scovant-core 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (278) hide show
  1. scovant_core-0.1.0/.gitignore +8 -0
  2. scovant_core-0.1.0/CHANGELOG.md +275 -0
  3. scovant_core-0.1.0/CODE_OF_CONDUCT.md +84 -0
  4. scovant_core-0.1.0/CONTRIBUTING.md +34 -0
  5. scovant_core-0.1.0/LICENSE +202 -0
  6. scovant_core-0.1.0/PKG-INFO +373 -0
  7. scovant_core-0.1.0/README.md +337 -0
  8. scovant_core-0.1.0/SECURITY.md +16 -0
  9. scovant_core-0.1.0/THIRD_PARTY_NOTICES.md +7 -0
  10. scovant_core-0.1.0/docs/checks.md +618 -0
  11. scovant_core-0.1.0/docs/core-vs-cloud.md +81 -0
  12. scovant_core-0.1.0/docs/example-report.md +638 -0
  13. scovant_core-0.1.0/docs/methodology.md +290 -0
  14. scovant_core-0.1.0/docs/profiles.md +55 -0
  15. scovant_core-0.1.0/docs/releasing.md +123 -0
  16. scovant_core-0.1.0/docs/report.schema.json +331 -0
  17. scovant_core-0.1.0/docs/security.md +324 -0
  18. scovant_core-0.1.0/fixtures/PROVENANCE.md +76 -0
  19. scovant_core-0.1.0/fixtures/html/blog_page.html +57 -0
  20. scovant_core-0.1.0/fixtures/html/product_page.html +73 -0
  21. scovant_core-0.1.0/fixtures/html/spa_shell.html +22 -0
  22. scovant_core-0.1.0/fixtures/sites/api-good/.well-known/agent-card.json +1 -0
  23. scovant_core-0.1.0/fixtures/sites/api-good/.well-known/oauth-authorization-server +1 -0
  24. scovant_core-0.1.0/fixtures/sites/api-good/.well-known/oauth-protected-resource +1 -0
  25. scovant_core-0.1.0/fixtures/sites/api-good/.well-known/security.txt +2 -0
  26. scovant_core-0.1.0/fixtures/sites/api-good/contact.html +2 -0
  27. scovant_core-0.1.0/fixtures/sites/api-good/docs/index.html +3 -0
  28. scovant_core-0.1.0/fixtures/sites/api-good/index.html +9 -0
  29. scovant_core-0.1.0/fixtures/sites/api-good/openapi.json +1 -0
  30. scovant_core-0.1.0/fixtures/sites/api-good/privacy.html +2 -0
  31. scovant_core-0.1.0/fixtures/sites/api-good/robots.txt +4 -0
  32. scovant_core-0.1.0/fixtures/sites/api-good/sitemap.xml +6 -0
  33. scovant_core-0.1.0/fixtures/sites/commerce-bad/.well-known/security.txt +1 -0
  34. scovant_core-0.1.0/fixtures/sites/commerce-bad/.well-known/ucp +1 -0
  35. scovant_core-0.1.0/fixtures/sites/commerce-bad/index.html.redirect +1 -0
  36. scovant_core-0.1.0/fixtures/sites/commerce-bad/llms.txt +5 -0
  37. scovant_core-0.1.0/fixtures/sites/commerce-bad/robots.txt +7 -0
  38. scovant_core-0.1.0/fixtures/sites/commerce-bad/step1.redirect +1 -0
  39. scovant_core-0.1.0/fixtures/sites/commerce-bad/step2.redirect +1 -0
  40. scovant_core-0.1.0/fixtures/sites/commerce-bad/step3.redirect +1 -0
  41. scovant_core-0.1.0/fixtures/sites/commerce-bad/step4.html +14 -0
  42. scovant_core-0.1.0/fixtures/sites/commerce-good/.well-known/mcp.json +1 -0
  43. scovant_core-0.1.0/fixtures/sites/commerce-good/.well-known/security.txt +3 -0
  44. scovant_core-0.1.0/fixtures/sites/commerce-good/.well-known/ucp +18 -0
  45. scovant_core-0.1.0/fixtures/sites/commerce-good/contact.html +3 -0
  46. scovant_core-0.1.0/fixtures/sites/commerce-good/index.html +9 -0
  47. scovant_core-0.1.0/fixtures/sites/commerce-good/index.html.headers +1 -0
  48. scovant_core-0.1.0/fixtures/sites/commerce-good/llms.txt +7 -0
  49. scovant_core-0.1.0/fixtures/sites/commerce-good/privacy.html +4 -0
  50. scovant_core-0.1.0/fixtures/sites/commerce-good/products/widget.html +10 -0
  51. scovant_core-0.1.0/fixtures/sites/commerce-good/returns.html +4 -0
  52. scovant_core-0.1.0/fixtures/sites/commerce-good/robots.txt +11 -0
  53. scovant_core-0.1.0/fixtures/sites/commerce-good/shipping.html +4 -0
  54. scovant_core-0.1.0/fixtures/sites/commerce-good/sitemap.xml +6 -0
  55. scovant_core-0.1.0/fixtures/sites/commerce-good/terms.html +4 -0
  56. scovant_core-0.1.0/fixtures/sites/expected/api-good.html +536 -0
  57. scovant_core-0.1.0/fixtures/sites/expected/api-good.json +1051 -0
  58. scovant_core-0.1.0/fixtures/sites/expected/api-good.md +446 -0
  59. scovant_core-0.1.0/fixtures/sites/expected/commerce-bad.html +608 -0
  60. scovant_core-0.1.0/fixtures/sites/expected/commerce-bad.json +1092 -0
  61. scovant_core-0.1.0/fixtures/sites/expected/commerce-bad.md +581 -0
  62. scovant_core-0.1.0/fixtures/sites/expected/commerce-good.html +619 -0
  63. scovant_core-0.1.0/fixtures/sites/expected/commerce-good.json +1125 -0
  64. scovant_core-0.1.0/fixtures/sites/expected/commerce-good.md +635 -0
  65. scovant_core-0.1.0/fixtures/sites/expected/saas-mixed.html +579 -0
  66. scovant_core-0.1.0/fixtures/sites/expected/saas-mixed.json +1080 -0
  67. scovant_core-0.1.0/fixtures/sites/expected/saas-mixed.md +535 -0
  68. scovant_core-0.1.0/fixtures/sites/saas-mixed/.well-known/oauth-authorization-server +1 -0
  69. scovant_core-0.1.0/fixtures/sites/saas-mixed/.well-known/oauth-protected-resource +1 -0
  70. scovant_core-0.1.0/fixtures/sites/saas-mixed/.well-known/security.txt +1 -0
  71. scovant_core-0.1.0/fixtures/sites/saas-mixed/contact.html +2 -0
  72. scovant_core-0.1.0/fixtures/sites/saas-mixed/docs/index.html +5 -0
  73. scovant_core-0.1.0/fixtures/sites/saas-mixed/index.html +17 -0
  74. scovant_core-0.1.0/fixtures/sites/saas-mixed/index.html.headers +1 -0
  75. scovant_core-0.1.0/fixtures/sites/saas-mixed/pricing.html +6 -0
  76. scovant_core-0.1.0/fixtures/sites/saas-mixed/privacy.html +4 -0
  77. scovant_core-0.1.0/fixtures/sites/saas-mixed/robots.txt +7 -0
  78. scovant_core-0.1.0/fixtures/sites/saas-mixed/signup.html +9 -0
  79. scovant_core-0.1.0/fixtures/sites/saas-mixed/sitemap.xml +7 -0
  80. scovant_core-0.1.0/fixtures/sites/saas-mixed/terms.html +4 -0
  81. scovant_core-0.1.0/npm/LICENSE +202 -0
  82. scovant_core-0.1.0/npm/README.md +75 -0
  83. scovant_core-0.1.0/pyproject.toml +92 -0
  84. scovant_core-0.1.0/src/scovant_core/__init__.py +20 -0
  85. scovant_core-0.1.0/src/scovant_core/__main__.py +12 -0
  86. scovant_core-0.1.0/src/scovant_core/_exports.py +47 -0
  87. scovant_core-0.1.0/src/scovant_core/action.py +219 -0
  88. scovant_core-0.1.0/src/scovant_core/analysis/__init__.py +3 -0
  89. scovant_core-0.1.0/src/scovant_core/analysis/form_semantics.py +60 -0
  90. scovant_core-0.1.0/src/scovant_core/analysis/instruction_integrity.py +195 -0
  91. scovant_core-0.1.0/src/scovant_core/analysis/integrity_probe.py +192 -0
  92. scovant_core-0.1.0/src/scovant_core/analysis/mcp_meta.py +248 -0
  93. scovant_core-0.1.0/src/scovant_core/analysis/page_cost.py +92 -0
  94. scovant_core-0.1.0/src/scovant_core/analysis/prices.py +67 -0
  95. scovant_core-0.1.0/src/scovant_core/analysis/tool_risk.py +47 -0
  96. scovant_core-0.1.0/src/scovant_core/analysis/webmcp_static.py +201 -0
  97. scovant_core-0.1.0/src/scovant_core/checks/__init__.py +22 -0
  98. scovant_core-0.1.0/src/scovant_core/checks/_document.py +44 -0
  99. scovant_core-0.1.0/src/scovant_core/checks/_truncation.py +60 -0
  100. scovant_core-0.1.0/src/scovant_core/checks/access/__init__.py +28 -0
  101. scovant_core-0.1.0/src/scovant_core/checks/access/_identities.py +12 -0
  102. scovant_core-0.1.0/src/scovant_core/checks/access/_robots_readability.py +50 -0
  103. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_001.py +33 -0
  104. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_002.py +73 -0
  105. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_003.py +58 -0
  106. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_004.py +65 -0
  107. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_005.py +74 -0
  108. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_006.py +88 -0
  109. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_007.py +68 -0
  110. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_008.py +37 -0
  111. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_009.py +78 -0
  112. scovant_core-0.1.0/src/scovant_core/checks/access/core_access_010.py +52 -0
  113. scovant_core-0.1.0/src/scovant_core/checks/base.py +90 -0
  114. scovant_core-0.1.0/src/scovant_core/checks/interfaces/__init__.py +26 -0
  115. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_001.py +93 -0
  116. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_002.py +99 -0
  117. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_003.py +81 -0
  118. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_004.py +100 -0
  119. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_005.py +70 -0
  120. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_006.py +76 -0
  121. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_007.py +74 -0
  122. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_008.py +68 -0
  123. scovant_core-0.1.0/src/scovant_core/checks/interfaces/core_interface_009.py +99 -0
  124. scovant_core-0.1.0/src/scovant_core/checks/machine/__init__.py +32 -0
  125. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_001.py +49 -0
  126. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_002.py +60 -0
  127. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_003.py +50 -0
  128. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_004.py +66 -0
  129. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_005.py +65 -0
  130. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_006.py +58 -0
  131. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_007.py +61 -0
  132. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_008.py +48 -0
  133. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_009.py +49 -0
  134. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_010.py +36 -0
  135. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_011.py +57 -0
  136. scovant_core-0.1.0/src/scovant_core/checks/machine/core_machine_012.py +84 -0
  137. scovant_core-0.1.0/src/scovant_core/checks/operability/__init__.py +22 -0
  138. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_001.py +59 -0
  139. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_002.py +45 -0
  140. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_003.py +44 -0
  141. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_004.py +95 -0
  142. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_005.py +112 -0
  143. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_006.py +62 -0
  144. scovant_core-0.1.0/src/scovant_core/checks/operability/core_operability_007.py +94 -0
  145. scovant_core-0.1.0/src/scovant_core/checks/registry.py +67 -0
  146. scovant_core-0.1.0/src/scovant_core/checks/trust/__init__.py +22 -0
  147. scovant_core-0.1.0/src/scovant_core/checks/trust/_policy.py +68 -0
  148. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_001.py +49 -0
  149. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_002.py +35 -0
  150. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_003.py +35 -0
  151. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_004.py +37 -0
  152. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_005.py +35 -0
  153. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_006.py +80 -0
  154. scovant_core-0.1.0/src/scovant_core/checks/trust/core_trust_007.py +95 -0
  155. scovant_core-0.1.0/src/scovant_core/cli.py +332 -0
  156. scovant_core-0.1.0/src/scovant_core/compat.py +26 -0
  157. scovant_core-0.1.0/src/scovant_core/context.py +38 -0
  158. scovant_core-0.1.0/src/scovant_core/contribute.py +59 -0
  159. scovant_core-0.1.0/src/scovant_core/docs.py +174 -0
  160. scovant_core-0.1.0/src/scovant_core/engine.py +177 -0
  161. scovant_core-0.1.0/src/scovant_core/evidence.py +58 -0
  162. scovant_core-0.1.0/src/scovant_core/gatherers/__init__.py +1 -0
  163. scovant_core-0.1.0/src/scovant_core/gatherers/_http.py +123 -0
  164. scovant_core-0.1.0/src/scovant_core/gatherers/_register.py +20 -0
  165. scovant_core-0.1.0/src/scovant_core/gatherers/_soft_200.py +57 -0
  166. scovant_core-0.1.0/src/scovant_core/gatherers/agent_discovery.py +68 -0
  167. scovant_core-0.1.0/src/scovant_core/gatherers/agent_discovery_surface.py +74 -0
  168. scovant_core-0.1.0/src/scovant_core/gatherers/agent_payments.py +117 -0
  169. scovant_core-0.1.0/src/scovant_core/gatherers/contact.py +52 -0
  170. scovant_core-0.1.0/src/scovant_core/gatherers/forms.py +33 -0
  171. scovant_core-0.1.0/src/scovant_core/gatherers/http.py +19 -0
  172. scovant_core-0.1.0/src/scovant_core/gatherers/link_headers.py +45 -0
  173. scovant_core-0.1.0/src/scovant_core/gatherers/llms.py +55 -0
  174. scovant_core-0.1.0/src/scovant_core/gatherers/machine_links.py +110 -0
  175. scovant_core-0.1.0/src/scovant_core/gatherers/machine_rep.py +97 -0
  176. scovant_core-0.1.0/src/scovant_core/gatherers/markdown.py +115 -0
  177. scovant_core-0.1.0/src/scovant_core/gatherers/mcp_discovery.py +109 -0
  178. scovant_core-0.1.0/src/scovant_core/gatherers/mcp_metadata.py +33 -0
  179. scovant_core-0.1.0/src/scovant_core/gatherers/oauth.py +109 -0
  180. scovant_core-0.1.0/src/scovant_core/gatherers/oauth_metadata.py +82 -0
  181. scovant_core-0.1.0/src/scovant_core/gatherers/openapi.py +164 -0
  182. scovant_core-0.1.0/src/scovant_core/gatherers/page_metrics.py +19 -0
  183. scovant_core-0.1.0/src/scovant_core/gatherers/pages.py +182 -0
  184. scovant_core-0.1.0/src/scovant_core/gatherers/policy_pages.py +175 -0
  185. scovant_core-0.1.0/src/scovant_core/gatherers/probe_tables.py +81 -0
  186. scovant_core-0.1.0/src/scovant_core/gatherers/reference_integrity.py +89 -0
  187. scovant_core-0.1.0/src/scovant_core/gatherers/robots_txt.py +54 -0
  188. scovant_core-0.1.0/src/scovant_core/gatherers/security_txt.py +81 -0
  189. scovant_core-0.1.0/src/scovant_core/gatherers/sitemap.py +54 -0
  190. scovant_core-0.1.0/src/scovant_core/gatherers/sitemap_urls.py +91 -0
  191. scovant_core-0.1.0/src/scovant_core/gatherers/ucp.py +30 -0
  192. scovant_core-0.1.0/src/scovant_core/mcp_server.py +163 -0
  193. scovant_core-0.1.0/src/scovant_core/models.py +107 -0
  194. scovant_core-0.1.0/src/scovant_core/parsers/__init__.py +1 -0
  195. scovant_core-0.1.0/src/scovant_core/parsers/bot_protection.py +169 -0
  196. scovant_core-0.1.0/src/scovant_core/parsers/content_signals.py +83 -0
  197. scovant_core-0.1.0/src/scovant_core/parsers/html.py +538 -0
  198. scovant_core-0.1.0/src/scovant_core/parsers/llms_txt.py +46 -0
  199. scovant_core-0.1.0/src/scovant_core/parsers/mcp.py +154 -0
  200. scovant_core-0.1.0/src/scovant_core/parsers/robots.py +102 -0
  201. scovant_core-0.1.0/src/scovant_core/parsers/ucp.py +137 -0
  202. scovant_core-0.1.0/src/scovant_core/profiles.py +56 -0
  203. scovant_core-0.1.0/src/scovant_core/py.typed +0 -0
  204. scovant_core-0.1.0/src/scovant_core/registry/__init__.py +1 -0
  205. scovant_core-0.1.0/src/scovant_core/registry/ai_bots.py +54 -0
  206. scovant_core-0.1.0/src/scovant_core/report/__init__.py +8 -0
  207. scovant_core-0.1.0/src/scovant_core/report/_cloud_matrix.py +45 -0
  208. scovant_core-0.1.0/src/scovant_core/report/_common.py +73 -0
  209. scovant_core-0.1.0/src/scovant_core/report/_cta.py +18 -0
  210. scovant_core-0.1.0/src/scovant_core/report/html.py +311 -0
  211. scovant_core-0.1.0/src/scovant_core/report/json.py +13 -0
  212. scovant_core-0.1.0/src/scovant_core/report/markdown.py +121 -0
  213. scovant_core-0.1.0/src/scovant_core/report/text.py +189 -0
  214. scovant_core-0.1.0/src/scovant_core/schema.py +84 -0
  215. scovant_core-0.1.0/src/scovant_core/scoring.py +70 -0
  216. scovant_core-0.1.0/src/scovant_core/security/__init__.py +1 -0
  217. scovant_core-0.1.0/src/scovant_core/security/client.py +265 -0
  218. scovant_core-0.1.0/src/scovant_core/security/policy.py +60 -0
  219. scovant_core-0.1.0/src/scovant_core/security/tld.py +10 -0
  220. scovant_core-0.1.0/src/scovant_core/security/url_safety.py +131 -0
  221. scovant_core-0.1.0/tests/__init__.py +0 -0
  222. scovant_core-0.1.0/tests/_fixture_server.py +84 -0
  223. scovant_core-0.1.0/tests/_source_tree.py +34 -0
  224. scovant_core-0.1.0/tests/conftest.py +351 -0
  225. scovant_core-0.1.0/tests/test_action.py +58 -0
  226. scovant_core-0.1.0/tests/test_ai_bots.py +42 -0
  227. scovant_core-0.1.0/tests/test_analysis_helpers.py +271 -0
  228. scovant_core-0.1.0/tests/test_checks_access.py +921 -0
  229. scovant_core-0.1.0/tests/test_checks_interfaces.py +523 -0
  230. scovant_core-0.1.0/tests/test_checks_interfaces_2.py +627 -0
  231. scovant_core-0.1.0/tests/test_checks_machine.py +326 -0
  232. scovant_core-0.1.0/tests/test_checks_machine_2.py +467 -0
  233. scovant_core-0.1.0/tests/test_checks_operability_2.py +480 -0
  234. scovant_core-0.1.0/tests/test_checks_trust_2.py +442 -0
  235. scovant_core-0.1.0/tests/test_checks_trust_operability.py +291 -0
  236. scovant_core-0.1.0/tests/test_cli.py +399 -0
  237. scovant_core-0.1.0/tests/test_client_security.py +232 -0
  238. scovant_core-0.1.0/tests/test_contribute.py +84 -0
  239. scovant_core-0.1.0/tests/test_docs.py +170 -0
  240. scovant_core-0.1.0/tests/test_document_status.py +29 -0
  241. scovant_core-0.1.0/tests/test_evidence.py +39 -0
  242. scovant_core-0.1.0/tests/test_fixture_server.py +61 -0
  243. scovant_core-0.1.0/tests/test_gatherers.py +825 -0
  244. scovant_core-0.1.0/tests/test_gatherers_core.py +341 -0
  245. scovant_core-0.1.0/tests/test_gatherers_more.py +331 -0
  246. scovant_core-0.1.0/tests/test_gatherers_protocol_metadata.py +640 -0
  247. scovant_core-0.1.0/tests/test_golden.py +156 -0
  248. scovant_core-0.1.0/tests/test_hardening_followups.py +385 -0
  249. scovant_core-0.1.0/tests/test_instruction_integrity.py +142 -0
  250. scovant_core-0.1.0/tests/test_integrity_probe.py +235 -0
  251. scovant_core-0.1.0/tests/test_mcp_meta.py +153 -0
  252. scovant_core-0.1.0/tests/test_mcp_server.py +95 -0
  253. scovant_core-0.1.0/tests/test_models.py +24 -0
  254. scovant_core-0.1.0/tests/test_no_cloud_imports.py +24 -0
  255. scovant_core-0.1.0/tests/test_npm_package.py +109 -0
  256. scovant_core-0.1.0/tests/test_parsers_domain.py +657 -0
  257. scovant_core-0.1.0/tests/test_parsers_html.py +357 -0
  258. scovant_core-0.1.0/tests/test_private_networks.py +183 -0
  259. scovant_core-0.1.0/tests/test_probe_tables.py +45 -0
  260. scovant_core-0.1.0/tests/test_profiles.py +108 -0
  261. scovant_core-0.1.0/tests/test_registry.py +185 -0
  262. scovant_core-0.1.0/tests/test_report.py +290 -0
  263. scovant_core-0.1.0/tests/test_report_common.py +83 -0
  264. scovant_core-0.1.0/tests/test_report_formats.py +76 -0
  265. scovant_core-0.1.0/tests/test_report_html.py +57 -0
  266. scovant_core-0.1.0/tests/test_report_markdown.py +79 -0
  267. scovant_core-0.1.0/tests/test_schema.py +35 -0
  268. scovant_core-0.1.0/tests/test_scoring.py +71 -0
  269. scovant_core-0.1.0/tests/test_security_suite.py +320 -0
  270. scovant_core-0.1.0/tests/test_tld.py +13 -0
  271. scovant_core-0.1.0/tests/test_tool_risk.py +57 -0
  272. scovant_core-0.1.0/tests/test_truncation_behaviour.py +197 -0
  273. scovant_core-0.1.0/tests/test_truncation_check_completeness.py +458 -0
  274. scovant_core-0.1.0/tests/test_truncation_contract.py +157 -0
  275. scovant_core-0.1.0/tests/test_truncation_document_labels.py +142 -0
  276. scovant_core-0.1.0/tests/test_truncation_helpers.py +33 -0
  277. scovant_core-0.1.0/tests/test_url_safety.py +150 -0
  278. scovant_core-0.1.0/tests/test_version.py +12 -0
@@ -0,0 +1,8 @@
1
+ __pycache__/
2
+ *.pyc
3
+ dist/
4
+ build/
5
+ *.egg-info/
6
+ .pytest_cache/
7
+ .ruff_cache/
8
+ npm/node_modules/
@@ -0,0 +1,275 @@
1
+ # Changelog
2
+
3
+ All notable changes to this project are documented here. The format follows
4
+ Keep a Changelog; versions follow semver. `ruleset_version` changes are called
5
+ out explicitly because scores are only comparable within one ruleset version.
6
+
7
+ ## [0.1.0] - 2026-09-12
8
+
9
+ ### Added
10
+ - Package skeleton, security layer (SSRF guard), parsers for robots.txt,
11
+ Content-Signal, llms.txt, MCP discovery, UCP profile, HTML
12
+ metadata/structured data, and the AI crawler registry.
13
+ - 45 deterministic checks (`ruleset_version` `2026.09`) across 5 categories
14
+ — 5 of the 45 are `experimental` (marked below): evaluated and reported
15
+ on every scan, but excluded from the Static Signal Score until
16
+ calibrated against real-world traffic and promoted:
17
+ - Access & Discovery (10) — `CORE-ACCESS-001` HTTPS reachability,
18
+ `CORE-ACCESS-002` robots.txt availability and syntax,
19
+ `CORE-ACCESS-003` AI search crawler policy,
20
+ `CORE-ACCESS-004` training vs. search crawler separation,
21
+ `CORE-ACCESS-005` sitemap availability,
22
+ `CORE-ACCESS-006` sitemap freshness,
23
+ `CORE-ACCESS-007` canonical URL integrity,
24
+ `CORE-ACCESS-008` indexability,
25
+ `CORE-ACCESS-009` llms.txt presence and integrity,
26
+ `CORE-ACCESS-010` Content-Signal declaration
27
+ - Machine Understanding (12) — `CORE-MACHINE-001` JSON-LD parseability,
28
+ `CORE-MACHINE-002` Organization entity,
29
+ `CORE-MACHINE-003` WebSite/WebPage entity,
30
+ `CORE-MACHINE-004` Product structured data,
31
+ `CORE-MACHINE-005` Offer price/currency/availability,
32
+ `CORE-MACHINE-006` product identifier count,
33
+ `CORE-MACHINE-007` breadcrumbs,
34
+ `CORE-MACHINE-008` metadata quality,
35
+ `CORE-MACHINE-009` heading structure,
36
+ `CORE-MACHINE-010` language declaration,
37
+ `CORE-MACHINE-011` image alt coverage,
38
+ `CORE-MACHINE-012` visible vs. structured price (experimental)
39
+ - Agent Interfaces (9) — `CORE-INTERFACE-001` MCP discovery presence,
40
+ `CORE-INTERFACE-002` MCP server declaration quality,
41
+ `CORE-INTERFACE-003` WebMCP static presence,
42
+ `CORE-INTERFACE-004` WebMCP tool declaration quality (experimental),
43
+ `CORE-INTERFACE-005` OpenAPI discovery,
44
+ `CORE-INTERFACE-006` OAuth authorization-server metadata,
45
+ `CORE-INTERFACE-007` OAuth protected-resource metadata,
46
+ `CORE-INTERFACE-008` UCP profile validity (experimental),
47
+ `CORE-INTERFACE-009` agent discovery surface presence — A2A cards,
48
+ AI-plugin manifests, agents.json, Agent Skills (experimental)
49
+ - Trust & Commerce (7) — `CORE-TRUST-001` contact/support
50
+ discoverability, `CORE-TRUST-002` shipping policy discoverability,
51
+ `CORE-TRUST-003` returns/refund policy discoverability,
52
+ `CORE-TRUST-004` privacy policy discoverability,
53
+ `CORE-TRUST-005` terms/conditions discoverability,
54
+ `CORE-TRUST-006` security.txt discoverability,
55
+ `CORE-TRUST-007` pricing discoverability
56
+ - Operability & Efficiency (7) — `CORE-OPERABILITY-001`
57
+ server-rendered core content, `CORE-OPERABILITY-002` redirect chain
58
+ complexity, `CORE-OPERABILITY-003` cache validators,
59
+ `CORE-OPERABILITY-004` broken machine-consumable endpoints,
60
+ `CORE-OPERABILITY-005` agent parse cost, `CORE-OPERABILITY-006`
61
+ form/control labels, `CORE-OPERABILITY-007` machine reference
62
+ integrity (experimental; its gatherer runs only under `--experimental`
63
+ — the only gatherer whose requests leave the target's own origin)
64
+ - `scovant scan` CLI (`scovant`/`scovant check`) with `--profile`,
65
+ `--format text|json`, `--min-score`, `--fail-on`, `--timeout`,
66
+ `--max-pages`, `--user-agent`, `--include`/`--exclude`, `--experimental`,
67
+ `--token-chars-ratio` (characters-per-token estimate for
68
+ `CORE-OPERABILITY-005`'s page-cost evidence, default 4), `--quiet`,
69
+ `--no-color`, `--verbose`, and a stable exit-code contract (0 ok, 1
70
+ threshold, 2 invalid input, 3 network, 4 security block, 5 internal
71
+ error).
72
+ - Human-readable text report and a versioned JSON report
73
+ (`schema_version` `1.0`), both driven off one `Report` model.
74
+ - Network safety model: scheme allow-list, DNS/literal-IP SSRF guard
75
+ re-checked on every redirect hop, a driven (not automatic) redirect loop
76
+ capped at 5 hops, per-kind response size caps, connect/request/total-budget
77
+ timeouts — see `docs/security.md`.
78
+ - Deterministic profile resolution (`content`/`commerce`/`saas`/`api`) —
79
+ see `docs/profiles.md`.
80
+ - Golden-report regression tests for four canonical fixture sites —
81
+ `commerce-good` (100, A), `commerce-bad` (35, F), `api-good` (89, B),
82
+ `saas-mixed` (80, B) — plus unit tests for every parser, gatherer, and
83
+ check.
84
+ - Evidence-honesty rules applied uniformly across the checks:
85
+ - A reference the scanner could not fetch (`status: null`) is reported as
86
+ `unresolved`, never as a broken link — whatever declared it. When
87
+ nothing could be read at all, the check is `ERROR`, not `PASS`.
88
+ - A declared MCP endpoint is recorded but never judged: it speaks
89
+ JSON-RPC over POST and Core never performs the handshake, so whatever it
90
+ answers to a GET is `inconclusive`.
91
+ - A 200 response carrying an HTML page where a machine document was
92
+ requested (a catch-all router / soft-404 template) is treated as the
93
+ document being ABSENT — for `robots.txt`, sitemaps, `llms.txt` and
94
+ OpenAPI specs alike — and recorded as `served_as_html`. OpenAPI
95
+ discovery keeps probing the remaining candidates instead of locking
96
+ onto such a response.
97
+ - An unresolvable hostname is a network failure (CLI exit 3), not a
98
+ security block (exit 4): nothing was blocked, the name does not exist.
99
+ - A report whose entry URL never answered carries `final_url: null`.
100
+ - Sitemap and MCP server-card probes follow redirects through the guarded
101
+ client, so a document declared behind a 301 is found rather than reported
102
+ as absent.
103
+ - The text report prints `(evaluated/applicable)` check counts beside each
104
+ category score, and an `Experimental (not scored)` block listing any
105
+ experimental check that evaluated to something other than `N/A` (or a
106
+ one-line notice when none did); `docs/methodology.md` documents the
107
+ per-category check/weight distribution.
108
+ - Documented, capped request budget per scan beyond the entry-page fetch
109
+ and always-on discovery documents: policy pages ≤5, `security.txt` ≤2,
110
+ OAuth metadata 2, UCP profile 1, agent discovery surfaces ≤10 (≤11 when
111
+ the OpenAPI document was found at a path other than `/openapi.json` —
112
+ three of the thirteen conventional paths, the OpenAPI root document and
113
+ the two OAuth discovery documents, are shared documents another gatherer
114
+ already fetched this scan, so a DEFINITIVE earlier answer (a real 200 +
115
+ real JSON, a genuine 404/410, or a soft-200 HTML catch-all) is recorded
116
+ from that read instead of being probed a second time; an inconclusive
117
+ earlier read is never guessed into an answer and is probed directly),
118
+ machine reference integrity ≤20 (`--experimental` only — the only
119
+ gatherer gated on the flag, zero requests without it) — see
120
+ `docs/security.md`.
121
+ - The machine reference integrity probe (`analysis/integrity_probe.py`) is
122
+ routed through the same guarded `SecureClient` every other gatherer
123
+ uses for its package-registry lookups (SSRF guard, size cap, and a
124
+ refusal of any redirect that would leave the requested registry host —
125
+ no cross-host hop is followed even when the hop itself is a safe public
126
+ address); DNS lookups for domain references remain their own, separate,
127
+ HTTP-free resolution. It only ever runs under `--experimental` and is
128
+ bounded by the ≤20-lookup budget above.
129
+ - `--format markdown` — the same `Report` rendered as GitHub-flavored
130
+ Markdown (score table, per-category breakdown, findings grouped by
131
+ status with collapsible evidence) for pasting into a PR or issue.
132
+ - `--format html` — the same `Report` rendered as one self-contained HTML
133
+ document (inline CSS, no external resources, no JavaScript) suitable to
134
+ open directly in a browser or attach as a CI artifact. Both new
135
+ renderers are plain Python over the existing `Report` model
136
+ (`html.escape` for HTML) — no template-engine dependency added.
137
+ - `--allow-private-networks` — an explicit, off-by-default opt-in that
138
+ lifts the SSRF address block for the scan's target host only (every
139
+ other protection — scheme allow-list, redirect re-check, size caps,
140
+ request budget — stays in force); the CLI and the GitHub Action's
141
+ `allow-private-networks` input both map to the same
142
+ `SecurityPolicy.allow_private_networks` flag, and every report format
143
+ prints a one-line notice when it was used. See `docs/security.md` §
144
+ Private-network targets (opt-in) — the match is on the exact hostname
145
+ string you typed (`localhost` does not cover `127.0.0.1`).
146
+ - Composite GitHub Action (`action.yml` at the package root, so
147
+ `uses: Scovant/scovant-core@v1` runs it): installs itself from the
148
+ checked-out ref (`pip install "$GITHUB_ACTION_PATH"`, no PyPI
149
+ round-trip, no version skew between the pinned tag and the code that
150
+ runs), scans one URL, writes a Markdown Step Summary, uploads the full
151
+ report as a workflow artifact, and fails the step per its
152
+ `min-core-score`/`fail-on` gate. Inputs: `url`, `profile`,
153
+ `min-core-score`, `fail-on`, `experimental`, `timeout`, `report-format`,
154
+ `allow-private-networks`. Outputs: `score`, `grade`, `pass_count`,
155
+ `warn_count`, `fail_count`, `report_path`. One URL, one run, no state,
156
+ no comparison across runs — see the README's "Free boundary" note for
157
+ where Scovant Monitor picks up.
158
+ - `scovant mcp` — a stdio MCP server behind the optional `[mcp]` extra
159
+ (`mcp>=1.28,<2`), exposing five read-only tools (`scan_site`,
160
+ `get_core_score`, `list_checks`, `explain_check`, `get_finding`) so an
161
+ agent host can run a passive scan as a tool call instead of a shell
162
+ command. Single-flight (one scan at a time) and keeps only the last 8
163
+ reports in memory for `get_finding` to read back; never opens a browser,
164
+ never performs an MCP `initialize`/`tools/call` against the *scanned*
165
+ site, never authenticates.
166
+ - One shared `document_status()` rule backs every one of the nine checks
167
+ that classify a single well-known document fetch (robots.txt, sitemaps,
168
+ llms.txt, MCP/OpenAPI/OAuth/UCP/`security.txt` discovery) — see
169
+ `docs/methodology.md` § The status model for the exact ERROR/N/A/PASS
170
+ boundary it enforces.
171
+ - Discovery-surface probe budget: ≤13 candidate requests per scan, ≤10
172
+ when all three shared documents (OpenAPI at `/openapi.json`, both OAuth
173
+ well-knowns) gave a definitive earlier answer — an inconclusive earlier
174
+ read (5xx/401/403/error/a different path) is re-probed directly instead
175
+ of being guessed. See the request-budget bullet above.
176
+ - Documentation: `docs/methodology.md`, `docs/checks.md` (generated),
177
+ `docs/core-vs-cloud.md`, `docs/security.md`, `docs/profiles.md`,
178
+ `docs/releasing.md`.
179
+ - Published, generated JSON schema for the report (`docs/report.schema.json`,
180
+ JSON Schema draft 2020-12) — `scovant_core.schema.report_schema()` derives
181
+ it from the `Report` pydantic model, `python -m scovant_core.schema`
182
+ writes it, and a test pins the committed file to the generator and
183
+ validates every golden fixture and every MCP tool's `inputSchema` against
184
+ it. Adding a report field never bumps `schema_version`; removing or
185
+ retyping one does — see `docs/methodology.md` § Report schema.
186
+ - `--contribute` — opt-in, off by default: after a scan completes, sends
187
+ one HTTPS POST to a single fixed URL with an aggregate-only measurement
188
+ (`domain`, `timestamp`, `core_version`, `ruleset_version`,
189
+ `ruleset_digest`, `profile`, `experimental`, `check_statuses`, `score`)
190
+ for the community index at scovant.com/research. No page content, no
191
+ evidence, no IP address is ever sent. Never blocks or changes the exit
192
+ code; refused (exit 2) together with `--allow-private-networks`. See the
193
+ README's "Community contributions" section and `docs/security.md` §
194
+ Outbound requests.
195
+ - `@scovant/core` — a thin npm launcher (`npm/`) that runs the Python
196
+ engine rather than reimplementing any of it: it resolves a runner in
197
+ order (`uvx`, then `pipx`, then `python3 -m scovant_core`), each pinned
198
+ to the exact npm package version, and exits 9 when none is usable. The
199
+ package's own `src/scovant_core/__main__.py` was added so the third
200
+ fallback (`python3 -m scovant_core`) actually works. Published to npm
201
+ from a tag-triggered `publish_npm` job that runs only after the PyPI
202
+ `release` job succeeds, behind its own reviewer-gated environment; it
203
+ does not use `--provenance` — npm cannot attest provenance from a
204
+ private source repository — and that limitation is documented in the
205
+ runbook and the npm README. The `python3 -m scovant_core` fallback is the
206
+ one path that cannot pin the version, so the launcher compares the
207
+ version that interpreter reports with its own and warns on stderr,
208
+ naming both, before running it — it never substitutes an engine version
209
+ silently. A probe killed by its own timeout is reported as a timeout
210
+ (with `SCOVANT_NPM_PROBE_TIMEOUT_MS` to raise the budget), never as a
211
+ missing tool, and the published tarball carries the Apache-2.0 licence
212
+ text.
213
+ - `docs/example-report.md` — a full example report rendered from the
214
+ `commerce-good` golden fixture via `python -m scovant_core.docs
215
+ --example`, generated rather than hand-written, and pinned by a test
216
+ so it can never drift from the renderer or the fixture.
217
+
218
+ ### Changed
219
+ - A verdict drawn from a document the fetch layer cut off at its per-kind
220
+ byte cap now declares that partial read wherever it happens, not only on
221
+ the four robots.txt-derived checks (`CORE-ACCESS-002`, `-003`, `-004`,
222
+ `-010`) that used to be the whole contract. The truncation flag travels
223
+ from the fetch layer through every body-reading gatherer to the checks:
224
+ such a finding records `"truncated": true` in its evidence, caps its
225
+ confidence at `medium`, and says so in its summary — on every branch,
226
+ including a `FAIL`, since a partial read can invert a verdict in either
227
+ direction. 41 of the 45 checks participate; the remaining four
228
+ (`CORE-ACCESS-001`, `CORE-OPERABILITY-002`, `-003`, `-004`) are audited
229
+ exemptions whose verdict is drawn from status codes, response headers, or
230
+ the redirect chain — data a byte cap cannot affect. Truncation does not
231
+ change a verdict: the same site scans to the same statuses and the same
232
+ score whether a document was read in full or cut off, which a parity test
233
+ asserts directly, and the set of checks carrying the flag is pinned so the
234
+ coverage cannot shrink unnoticed. (The one status change on this release
235
+ is separate and deliberate — see the JSON-probe entry below.) Three
236
+ further tests make the contract structural rather than a convention — one
237
+ enumerates the gatherers, one enumerates the checks, and one walks every
238
+ individual verdict branch of every participating check, so a check that
239
+ declares on one branch and stays silent on another fails rather than
240
+ passing on the strength of its other branches.
241
+ `docs/methodology.md` and `docs/security.md` describe the wider
242
+ contract; reports produced before it are identified by
243
+ `provenance.core_version` / `core_version`.
244
+ - The shared JSON probe used to answer "truncated" and "not valid JSON"
245
+ identically, so an oversized document was reported as ABSENT. It now
246
+ distinguishes the two, and `CORE-INTERFACE-001` (MCP discovery presence)
247
+ reports `ERROR` for an MCP server card it could not read in full instead
248
+ of claiming the card is not there. **This is the one status change in this
249
+ release, and it can move a report's outcome.** An `ERROR` counts toward a
250
+ category's applicable weight, so a site whose only unreadable document is
251
+ an oversized server card can now fall below the evidence-coverage floor
252
+ and be reported as `INSUFFICIENT_EVIDENCE` rather than scored. That is the
253
+ intended trade: a document we could not read is not a document that is
254
+ absent, and reporting "no MCP discovery file is published" about a file we
255
+ never finished reading is the over-claim this release exists to remove.
256
+ It cannot fire on a genuinely absent document — a real 404 still yields a
257
+ confirmed absence, which a test pins alongside the `ERROR` case.
258
+ - `CORE-OPERABILITY-005` states a token estimate taken from a truncated
259
+ page as a floor ("at least N tokens"), so a partial read can no longer
260
+ read as a measurement that came in under the threshold. The cost band
261
+ follows the sentence: on a partial read the finding's evidence reports
262
+ `level: null` with `level_at_least` naming the band, instead of asserting
263
+ a below-threshold classification the floor cannot support.
264
+
265
+ ### Fixed
266
+ - Every report format (Markdown, HTML, and text) now accounts for every
267
+ check it counts: the header/summary line counts all 45 checks, but
268
+ experimental `N/A` findings appeared in no section of the body, so the
269
+ arithmetic did not reconcile (37 PASS + 8 N/A with only 5 N/A listed).
270
+ They are now listed as bare ids — in the "Experimental (not scored)"
271
+ section for Markdown and HTML, and on the same compact "N/A: ..." line
272
+ for text. Statuses, scoring and applicability are unchanged — this is a
273
+ rendering fix.
274
+ - `cli.py`'s `_PROFILES` is now imported from `scovant_core.profiles`
275
+ instead of a second, hand-duplicated tuple.
@@ -0,0 +1,84 @@
1
+
2
+ # Contributor Covenant Code of Conduct
3
+
4
+ ## Our Pledge
5
+
6
+ We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, caste, color, religion, or sexual identity and orientation.
7
+
8
+ We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
9
+
10
+ ## Our Standards
11
+
12
+ Examples of behavior that contributes to a positive environment for our community include:
13
+
14
+ * Demonstrating empathy and kindness toward other people
15
+ * Being respectful of differing opinions, viewpoints, and experiences
16
+ * Giving and gracefully accepting constructive feedback
17
+ * Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
18
+ * Focusing on what is best not just for us as individuals, but for the overall community
19
+
20
+ Examples of unacceptable behavior include:
21
+
22
+ * The use of sexualized language or imagery, and sexual attention or advances of any kind
23
+ * Trolling, insulting or derogatory comments, and personal or political attacks
24
+ * Public or private harassment
25
+ * Publishing others' private information, such as a physical or email address, without their explicit permission
26
+ * Other conduct which could reasonably be considered inappropriate in a professional setting
27
+
28
+ ## Enforcement Responsibilities
29
+
30
+ Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
31
+
32
+ Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
33
+
34
+ ## Scope
35
+
36
+ This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
37
+
38
+ ## Enforcement
39
+
40
+ Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at security@scovant.com. All complaints will be reviewed and investigated promptly and fairly.
41
+
42
+ All community leaders are obligated to respect the privacy and security of the reporter of any incident.
43
+
44
+ ## Enforcement Guidelines
45
+
46
+ Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
47
+
48
+ ### 1. Correction
49
+
50
+ **Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
51
+
52
+ **Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
53
+
54
+ ### 2. Warning
55
+
56
+ **Community Impact**: A violation through a single incident or series of actions.
57
+
58
+ **Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
59
+
60
+ ### 3. Temporary Ban
61
+
62
+ **Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
63
+
64
+ **Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
65
+
66
+ ### 4. Permanent Ban
67
+
68
+ **Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
69
+
70
+ **Consequence**: A permanent ban from any sort of public interaction within the community.
71
+
72
+ ## Attribution
73
+
74
+ This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.1, available at [https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
75
+
76
+ Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder][Mozilla CoC].
77
+
78
+ For answers to common questions about this code of conduct, see the FAQ at [https://www.contributor-covenant.org/faq][FAQ]. Translations are available at [https://www.contributor-covenant.org/translations][translations].
79
+
80
+ [homepage]: https://www.contributor-covenant.org
81
+ [v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
82
+ [Mozilla CoC]: https://github.com/mozilla/diversity
83
+ [FAQ]: https://www.contributor-covenant.org/faq
84
+ [translations]: https://www.contributor-covenant.org/translations
@@ -0,0 +1,34 @@
1
+ # Contributing
2
+
3
+ Thank you for helping make AI-agent readiness measurable.
4
+
5
+ ## How changes land
6
+
7
+ This repository is a mirror. Pull requests are welcome and are reviewed here,
8
+ but they are merged in Scovant's development monorepo and appear here in the
9
+ next sync commit with your authorship preserved as a co-author trailer.
10
+ Please do not be surprised when your PR is closed with a reference to the
11
+ sync commit that contains it.
12
+
13
+ ## What we accept
14
+
15
+ New deterministic checks, parser improvements, support for new public
16
+ standards, test fixtures, output formats, documentation.
17
+
18
+ A new check must satisfy at least four of: machine-verifiable, deterministic,
19
+ reproducible, useful across many sites, linked to an authoritative standard,
20
+ meaningful to agent access/understanding/action, low operational cost, safe
21
+ to evaluate passively. Checks that need a real agent or a browser session
22
+ belong to Scovant Cloud, not here.
23
+
24
+ ## Requirements for every PR
25
+
26
+ - tests for every parser or check touched (fixtures must be synthetic — see
27
+ `fixtures/PROVENANCE.md`);
28
+ - no network access in unit tests;
29
+ - no new runtime dependency without discussion;
30
+ - `ruff check` and `pytest` green.
31
+ - `mypy src` clean.
32
+ - A ruleset change must update the golden reports explicitly
33
+ (`SCOVANT_CORE_UPDATE_GOLDENS=1 pytest tests/test_golden.py`) and the diff
34
+ must be reviewed.
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright 2026 Scovant
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.