spellwarden 0.1.0__py3-none-any.whl

spellwarden-0.1.0.dist-info/METADATA

@@ -0,0 +1,143 @@
+Metadata-Version: 2.5
+Name: spellwarden
+Version: 0.1.0
+Summary: The Spellwarden scan engine: baseline rules for agent skills and MCP servers, probe classification, migration checklist and curation score. Pure code, no I/O.
+Project-URL: Homepage, https://spellwarden.ai
+Project-URL: Source, https://github.com/spellwarden-ai/spellwarden
+Author: Spellwarden
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: agent-skills,mcp,scanner,security
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Security
+Requires-Python: >=3.11
+Requires-Dist: pyyaml>=6.0
+Description-Content-Type: text/markdown
+
+# spellwarden
+
+The Spellwarden scan engine: the baseline rules for agent skills and MCP servers, the probe classification against the 2026-07-28 MCP specification, the migration checklist and the curation score. It is the engine of the hosted product at [spellwarden.ai](https://spellwarden.ai) and is published so that the same rules run in your own tooling.
+
+This package is pure code. It never opens a connection, reads a file or an environment variable: you hand it the bytes of a package or the recorded result of a probe, and it hands back findings. The command-line scanner, discovery in a repository and the CI wrappers arrive in a later release; this one is the library they are built on.
+
+```
+pip install spellwarden
+```
+
+Python 3.11 or newer. The only dependency is PyYAML.
+
+## Scanning a skill package
+
+```python
+from spellwarden_scan import RuleSet, scan_skill_package, unpack_zip
+
+files, executable = unpack_zip(open_bytes, with_modes=True)   # or any {path: bytes} mapping you built yourself
+result = scan_skill_package(files, RuleSet.baseline(), executable_paths=executable)
+for finding in result.findings:
+    print(finding.rule_id, finding.severity, finding.location.path, finding.location.line, finding.evidence)
+print(result.sha256, result.metadata.name, result.truncated)
+```
+
+- `files` maps POSIX relative paths to bytes. `root` names the directory that holds `SKILL.md` when it is not the package root.
+- `unpack_zip(data, limits=ArchiveLimits(), with_modes=False)` reads a zip held in memory and refuses unsafe archives with an `ArchiveError` whose `code` is one of `too_large`, `too_many_files`, `unsafe_path`, `symlink`, `bad_zip`, `empty`. The default limits are 20 MiB compressed, 50 MiB uncompressed, 2000 files, 10 MiB per file.
+- `result.sha256` is the canonical hash of the package: SHA-256 over `path NUL content NUL` for every path in sorted order, stable across archive layout.
+- `result.metadata` holds `name`, `description`, `version`, `license`, `publisher` from the frontmatter (nested `metadata:` keys and `author` are read too), which of them are present, and the problems that rule SW-SKL-015 reports.
+- `max_findings` (500) and `max_per_rule` (100) bound what the scan keeps; rules run worst severity first and `result.truncated` counts the matches that were not kept.
+- Evidence is at most 300 characters and credential-shaped text in it is masked. `fingerprint` is the SHA-256 of rule id, path and matched text, so a finding keeps its identity across scans.
+
+## Evaluating an MCP server probe
+
+```python
+from spellwarden_scan import ProbeResult, RuleSet, evaluate_probe
+
+probe = ProbeResult.from_dict(recorded)      # what your prober recorded; every field has a default
+result = evaluate_probe(probe, RuleSet.baseline())
+print(result.transport, result.auth_mode, result.spec_version, result.migration_status)
+for item in result.checklist:
+    print(item.order, item.text)
+```
+
+`ProbeResult` is the record of an unauthenticated probe: the `server/discover` or `initialize` result, the status and content type of the POST and GET, whether a session header was seen, the `tools/list` answer, the RFC 9728 protected resource metadata and the authorization server metadata. The classification follows one rule set:
+
+- transport: `streamable-http`, `sse`, `stdio` (a repository without an endpoint) or `unknown`;
+- authentication: `none`, `static-key`, `oauth-dcr`, `oauth-cimd`, `xaa` or `unknown`;
+- spec version: the highest `supportedVersions` date of `server/discover`, else the negotiated `initialize` version;
+- deprecated features, in a fixed order: `sse`, `initialize_only`, `sessions`, `roots`, `sampling`, `logging`, `dcr`;
+- `migration_status`: `ready` when the spec version is 2026-07-28 or later, authentication is CIMD or XAA and nothing deprecated is in use; `to_migrate` otherwise; `not_probeable` for stdio servers.
+
+The checklist has twelve items in a fixed order, each present only when it applies (move to streamable HTTP; add `server/discover`; remove sessions; carry the protocol version and capabilities in `_meta`; replace `sampling/createMessage` with an `input_required` result; replace Logging with a per-request `_meta` log level; move long jobs to the Tasks extension; register a Client ID Metadata Document and enable OAuth with RFC 9728 and RFC 8707; validate `iss`; set `ttlMs` and `cacheScope` on list results; propagate `traceparent`; re-run the scan, which is always last).
+
+## Curation score
+
+```python
+from spellwarden_scan import CurationInputs, curation_score, is_curated, is_quarantined
+
+inputs = CurationInputs(open_findings=open_ones, accepted_findings=accepted_ones, metadata_present=5, eval_component=0.5)
+score = curation_score(inputs)          # 0 to 12, one decimal
+curated = is_curated(inputs, score)     # score >= 8, no open critical or high finding, hash unchanged, not quarantined
+quarantined = is_quarantined(open_ones) # any open finding from a malicious-indicator rule
+```
+
+The score is `12 x (0.6 S + 0.2 M + 0.2 E)`: `S = max(0, 1 - (6 critical + 3 high + 1 medium + 0.25 low) / 12)` over open findings with accepted findings at half weight, `M` the share of the five metadata fields present, `E` an evaluation component that is 0.5 until evaluations exist.
+
+## The rules
+
+Ids are `SW-SKL-NNN` (skill packages) and `SW-MCP-NNN` (MCP servers). Mappings use the OWASP Agentic Top 10 (ASI) and OWASP MCP Top 10 (MCP) identifiers and NIST SP 800-53 base controls, labelled as a provisional mapping to SP 800-53 base controls. Two rules are malicious indicators: an open finding from one of them quarantines the package.
+
+| Id | Title | Severity | OWASP | NIST |
+|---|---|---|---|---|
+| SW-SKL-001 | Prompt-injection phrases in skill instructions | high | ASI01 | SI-10 |
+| SW-SKL-002 | Hidden text: zero-width or bidirectional control characters | high | ASI01 | SI-10 |
+| SW-SKL-003 | Instructions to skip approvals or disable hooks | high | ASI10 | AC-6 |
+| SW-SKL-004 | Encoded payload decoded and executed (malicious indicator) | critical | ASI04 | SR-3 |
+| SW-SKL-005 | Writes to agent configuration | high | ASI10 | AC-6 |
+| SW-SKL-006 | Destructive command without a confirmation step | medium | ASI10 | AC-6 |
+| SW-SKL-007 | Remote script piped to a shell | high | ASI04 | SR-3 |
+| SW-SKL-008 | Sends local file contents to an external host (malicious indicator) | critical | ASI10 | SC-7 |
+| SW-SKL-009 | Unpinned dependency install | medium | ASI04 | SR-3 |
+| SW-SKL-010 | Bundled binary or executable file | medium | ASI04 | SR-3 |
+| SW-SKL-011 | Hard-coded credential in the package | critical | MCP01 | IA-5 |
+| SW-SKL-012 | Reads a credential file path without stating purpose | medium | ASI04 | IA-5 |
+| SW-SKL-013 | Network calls to raw IP addresses or URL shorteners | medium | ASI10 | SC-7 |
+| SW-SKL-014 | Obfuscated script code | medium | ASI04 | SR-3 |
+| SW-SKL-015 | Frontmatter missing or invalid (name, description) | low | ASI04 | SR-3 |
+| SW-SKL-019 | Fetches external URL content into context without an allowlist | medium | ASI01, MCP10 | SI-10 |
+| SW-SKL-031 | Missing license and version metadata | low | ASI04 | SR-3 |
+| SW-MCP-001 | Server lists tools without authentication | high | MCP01 | AC-3 |
+| SW-MCP-002 | Static key authentication instead of OAuth | medium | MCP01 | IA-5 |
+| SW-MCP-003 | OAuth dynamic client registration (deprecated; use Client ID Metadata Documents) | medium | MCP01 | IA-5 |
+| SW-MCP-004 | HTTP+SSE transport (deprecated) | medium | ASI04 | SR-3 |
+| SW-MCP-005 | Spec version older than 2026-07-28 | low | ASI04 | SR-3 |
+| SW-MCP-006 | Protocol sessions (Mcp-Session-Id) in use | medium | ASI04 | SR-3 |
+| SW-MCP-007 | Requires the initialize handshake; no server/discover | medium | ASI04 | SR-3 |
+| SW-MCP-008 | Uses deprecated Roots, Sampling or Logging | medium | ASI04 | SR-3 |
+| SW-MCP-009 | Endpoint not served over HTTPS | high | MCP01 | SC-7 |
+| SW-MCP-010 | No protected resource metadata, or issuer not validated | medium | MCP01 | IA-5 |
+| SW-MCP-011 | Tool description contains instruction-like text | high | ASI01, MCP10 | SI-10 |
+
+Ids 016 to 018 and 020 to 030 are reserved. `RuleSet.baseline()` returns these rules; `ruleset.with_rules(extra)` adds your own `Rule` objects built with `spellwarden_scan.rules.make_rule`.
+
+## Versions
+
+`spellwarden_scan.__version__` is the package version and `spellwarden_scan.RULES_VERSION` (`YYYY.MM.N`) the rule set's. A change to what any rule detects bumps both the rules version and the package minor version; a fix anywhere else bumps the patch. Every scan result carries both, so a stored finding always says which rules produced it.
+
+## Releases
+
+Releases are built and published by GitHub Actions through PyPI trusted publishing (OpenID Connect): a push of a tag `vX.Y.Z` whose version equals the one in `pyproject.toml` builds the sdist and the wheel and publishes them from the `pypi` environment. No API token exists anywhere. The sources are checked on Python 3.11, 3.12 and 3.13 on every push.
+
+## Development
+
+```
+make check     # ruff, pytest, uv build
+```
+
+`tests/test_pure.py` fails the build if any module reaches for the network, the file system or the environment; `tests/test_fixture_coverage.py` fails it if a rule lacks a positive or a negative fixture.
+
+## License
+
+Apache-2.0. See `LICENSE`.

spellwarden-0.1.0.dist-info/RECORD

@@ -0,0 +1,20 @@
+spellwarden_scan/__init__.py,sha256=QW2a7OOWwL8kTQoQNoqhiR2WPO7D986t4JXr5mQHyH8,1646
+spellwarden_scan/archive.py,sha256=Ul7RswMmuP7C1kzhWJ8quyh_CGRK-5DjmxdEUijhKfE,9916
+spellwarden_scan/canonical.py,sha256=IPs_uwK-uzC9ZfmU_BINiPBfQHNBhOu7UX4D9wgMKFw,534
+spellwarden_scan/checklist.py,sha256=8OfRUk_ZdDZSXIDDoQJan4oGafXKhYC6xTcQ09bMags,2614
+spellwarden_scan/curation.py,sha256=ECmxuCqVBwtZv4F24nkpvZnE0hQRMvpkO2RMyGoQ4Wk,2116
+spellwarden_scan/evidence.py,sha256=UIcvWNw0iLYxM0mFLdZZxjRfyUW9uJYZ1zv4gGW-k1s,4754
+spellwarden_scan/frontmatter.py,sha256=YrR2xjafDhY4CQ9JMHGWn2XzFYeCCW9ZN0BAWuyxYvw,4520
+spellwarden_scan/model.py,sha256=jgTcy3R1Q3IFC0YfXOlp64yD2tnHg9_oWCRAhCqZgUI,6339
+spellwarden_scan/package.py,sha256=7KPHFDi4eX5x1ydT_UPDxj8qDgsg5UAoO207JUIEIIc,6885
+spellwarden_scan/probe.py,sha256=ljdUfrtKabqHZZeNrIUhpL4tKNrlImJ1iUBuh5wyS_E,8109
+spellwarden_scan/scan.py,sha256=GivzsXl8ONCk3AzLES5gDHl4jomqFpQWZGipazU1vRo,2172
+spellwarden_scan/version.py,sha256=Fp8tbs_ZZjaED6W3Npgtc1bZrz_J9FP4niAaALmzLjQ,107
+spellwarden_scan/rules/__init__.py,sha256=iMCAozIkzr6JzOl35ZSBp15dY3SPosR3le_L5V4CokY,4194
+spellwarden_scan/rules/mcp.py,sha256=eaqV9to-QFo60VQmmugcANwb5G_8WHUxYtOYf2xmj7k,12802
+spellwarden_scan/rules/patterns.py,sha256=IM16KNPfYx1dnv9r4bcKTJbO-y6-2zqxFjD0rPQ497U,6893
+spellwarden_scan/rules/skill.py,sha256=T67oKhW58gq9Ewvpmlu0hI_Acc0_uK7Sv0_t6BfTVHw,33619
+spellwarden-0.1.0.dist-info/METADATA,sha256=P1LFmlNVLUy93dS6sb7CK0zIAQUkIjcBXbSqEmBXAqc,10207
+spellwarden-0.1.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+spellwarden-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+spellwarden-0.1.0.dist-info/RECORD,,

spellwarden-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.4
+Root-Is-Purelib: true
+Tag: py3-none-any

spellwarden-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

spellwarden_scan/__init__.py

@@ -0,0 +1,28 @@
+"""spellwarden_scan: the Spellwarden scan engine (spec 5). Pure code: it
+takes bytes and recorded probe results and returns findings. Tasks 2 to 4
+add `scan_skill_package`, `evaluate_probe`, `migration_checklist` and the
+curation functions to this list."""
+from __future__ import annotations
+
+from spellwarden_scan.archive import ArchiveError, ArchiveLimits, unpack_zip
+from spellwarden_scan.canonical import canonical_sha256
+from spellwarden_scan.evidence import mask_credentials
+from spellwarden_scan.frontmatter import FrontmatterError, parse_frontmatter
+from spellwarden_scan.model import (
+    SEVERITY_RANK, Area, AuthServerMetadata, ChecklistItem, CurationInputs, Finding, Location, McpScanResult, Metadata,
+    ProbeResult, Severity, SkillScanResult, ToolInfo,
+)
+from spellwarden_scan.checklist import migration_checklist
+from spellwarden_scan.curation import curation_score, is_curated, is_quarantined
+from spellwarden_scan.probe import evaluate_probe
+from spellwarden_scan.rules import Rule, RuleSet
+from spellwarden_scan.scan import scan_skill_package
+from spellwarden_scan.version import RULES_VERSION, __version__
+
+__all__ = [
+    "RULES_VERSION", "SEVERITY_RANK", "Area", "ArchiveError", "ArchiveLimits", "AuthServerMetadata", "ChecklistItem",
+    "CurationInputs", "Finding", "FrontmatterError", "Location", "McpScanResult", "Metadata", "ProbeResult", "Rule",
+    "RuleSet", "Severity", "SkillScanResult", "ToolInfo", "__version__", "canonical_sha256", "curation_score",
+    "evaluate_probe", "is_curated", "is_quarantined", "mask_credentials", "migration_checklist", "parse_frontmatter",
+    "scan_skill_package", "unpack_zip",
+]

spellwarden_scan/archive.py

@@ -0,0 +1,209 @@
+"""Zip unpacking with the safety rules of spec 5.6. The archive is bytes in
+memory; nothing touches the file system."""
+from __future__ import annotations
+
+import io
+import lzma
+import posixpath
+import re
+import stat
+import unicodedata
+import zipfile
+import zlib
+from dataclasses import dataclass
+
+_DRIVE = re.compile(r"^[A-Za-z]:")
+_CHUNK = 65536
+
+
+@dataclass(frozen=True)
+class ArchiveLimits:
+    max_compressed: int = 20 * 2**20
+    max_uncompressed: int = 50 * 2**20
+    max_files: int = 2000
+    max_file: int = 10 * 2**20
+    max_path: int = 255
+
+
+DEFAULT_LIMITS = ArchiveLimits()
+
+
+class ArchiveError(ValueError):
+    """`code` is one of `too_large`, `too_many_files`, `unsafe_path`, `symlink`, `bad_zip`, `empty`."""
+
+    def __init__(self, code: str, detail: str = "") -> None:
+        super().__init__(f"{code}: {detail}" if detail else code)
+        self.code = code
+        self.detail = detail
+
+
+def _unsafe(name: str, limits: ArchiveLimits) -> bool:
+    if not name or "\x00" in name or "\\" in name or _DRIVE.match(name) or name.startswith("/"):
+        return True
+    if len(name) > limits.max_path:
+        return True
+    parts = name.split("/")
+    # `.` and `..` anywhere, and empty parts (`a//b`): every consumer must read the same path the scan read.
+    return any(part in ("..", ".", "") for part in parts[:-1]) or parts[-1] in ("..", ".")
+
+
+def _platform_unsafe(name: str) -> bool:
+    """A part ending in a dot or a space, or holding `:`, is renamed or refused by Windows extractors (`run.sh.`
+    becomes `run.sh`): checked only under the scanned root (a repository may hold `docs/10:00.md` elsewhere)."""
+    return any(part.endswith((".", " ")) or ":" in part for part in name.split("/"))
+
+
+def _folded(name: str) -> str:
+    """The key two names collide on in a case-insensitive, normalising file system (Windows, macOS): NFC and
+    `lower()` (not `casefold()`, which maps `ß` to `ss` where NTFS and APFS do not)."""
+    return unicodedata.normalize("NFC", name).lower()
+
+
+def _platform_key(name: str) -> str:
+    """The path as a case-insensitive, normalising Windows or macOS extractor writes it: each segment without its
+    trailing dots and spaces, NFC, lower-cased."""
+    return "/".join(_folded(part.rstrip(". ")) for part in name.split("/"))
+
+
+def _under(name: str, root: str | None) -> bool:
+    """Whether `name` lands under the scanned root on some file system: decided on the platform key, so
+    `Skill/SKILL.md` or `skill./x` is under `skill` too (a macOS or Windows extractor merges them)."""
+    if root is None:
+        return False
+    if not root:
+        return True
+    key, scope = _platform_key(name), _platform_key(root)
+    return key == scope or key.startswith(scope + "/")
+
+
+def _is_special(info: zipfile.ZipInfo) -> bool:
+    mode = info.external_attr >> 16
+    return stat.S_ISLNK(mode) or stat.S_ISCHR(mode) or stat.S_ISBLK(mode) or stat.S_ISFIFO(mode) or stat.S_ISSOCK(mode)
+
+
+def _is_executable(info: zipfile.ZipInfo) -> bool:
+    mode = info.external_attr >> 16
+    return bool(mode & stat.S_IXUSR)
+
+
+def _strip_common_top(names: list[str]) -> str:
+    """The single top-level directory every entry shares, or an empty string."""
+    tops = {name.split("/", 1)[0] for name in names}
+    if len(tops) != 1:
+        return ""
+    top = tops.pop()
+    return top if all("/" in name for name in names) else ""
+
+
+def unpack_zip(data: bytes, limits: ArchiveLimits = DEFAULT_LIMITS, *, with_modes: bool = False, root: str | None = ""):
+    """`{path: bytes}` of a zip held in memory; with `with_modes=True`,
+    `(files, executable_paths)`. Raises `ArchiveError` (spec 5.6).
+
+    Everywhere in the archive, a repeated name, a `.`, `..` or empty segment and a file that is also a
+    directory are `unsafe_path` (every extractor reads them differently). Under `root` (the directory
+    that will be scanned, relative to the stripped top; `""` is the whole archive, `None` none of it),
+    two names equal after NFC normalisation and lower-casing and a segment Windows renames or refuses
+    are `unsafe_path` as well: outside it they belong to another directory of a repository."""
+    scope = None if root is None else root.strip("/")
+    if len(data) > limits.max_compressed:
+        raise ArchiveError("too_large", "compressed size over the limit")
+    try:
+        archive = zipfile.ZipFile(io.BytesIO(data))
+        infos = archive.infolist()
+    except (zipfile.BadZipFile, ValueError, EOFError, RuntimeError, OSError) as exc:
+        # `NotImplementedError` (a `RuntimeError`) for an unsupported "version needed to extract" in the central directory.
+        raise ArchiveError("bad_zip", str(exc)) from exc
+    for info in infos:
+        if info.is_dir() and _unsafe(info.filename.rstrip("/"), limits):
+            raise ArchiveError("unsafe_path", info.filename)
+    directories = [info.filename.rstrip("/") for info in infos if info.is_dir()]
+    entries = [info for info in infos if not info.is_dir()]
+    if not entries:
+        raise ArchiveError("empty")
+    if len(entries) > limits.max_files:
+        raise ArchiveError("too_many_files", str(len(entries)))
+    for info in entries:
+        if _unsafe(info.filename, limits):
+            raise ArchiveError("unsafe_path", info.filename)
+        if _is_special(info):
+            raise ArchiveError("symlink", info.filename)
+    _check_declared(entries, limits)
+    top = _strip_common_top([info.filename for info in entries])
+    files: dict[str, bytes] = {}
+    executable: set[str] = set()
+    folded: set[str] = set()
+    total = 0
+    for info in entries:
+        name = info.filename[len(top) + 1:] if top else info.filename
+        if _unsafe(name, limits) or posixpath.normpath(name) != name or name in files:
+            raise ArchiveError("unsafe_path", info.filename)
+        if _under(name, scope):
+            # Under the scanned root, a name that differs only in case or normalisation, or that Windows renames,
+            # would let an extractor install a file the scan never read; so would a name an extractor merges into the
+            # root that is not under it byte for byte (`Skill/run.sh` for `skill`: the scan reads `skill/` only).
+            exact = not scope or name == scope or name.startswith(scope + "/")
+            if not exact or _platform_unsafe(name) or _platform_key(name) in folded:
+                raise ArchiveError("unsafe_path", f"colliding {info.filename}")
+            folded.add(_platform_key(name))
+        content, total = _read_entry(archive, info, limits, total)
+        files[name] = content
+        if _is_executable(info):
+            executable.add(name)
+    _check_file_directory_clash(files, [d[len(top) + 1:] if top and d.startswith(top + "/") else d for d in directories], scope)
+    if with_modes:
+        return files, frozenset(executable)
+    return files
+
+
+def _check_file_directory_clash(files: dict[str, bytes], directories: list[str], scope: str | None) -> None:
+    """`a/b` as a file and `a/b/c` (or a directory entry `a/b/`) as another: no file system holds both, so an
+    extractor keeps one of them. Exact names everywhere; under the scanned root also case- and NFC-folded."""
+    exact = set(files)
+    folded = {_platform_key(name) for name in files if _under(name, scope)}
+    directory_set = set(directories)
+    for name in list(files) + directories:
+        parts = name.split("/")
+        for depth in range(1, len(parts) + (name in directory_set)):
+            prefix = "/".join(parts[:depth])
+            if prefix in exact or (_under(prefix, scope) and _platform_key(prefix) in folded):
+                raise ArchiveError("unsafe_path", f"file and directory {name}")
+
+
+def _check_declared(entries: list[zipfile.ZipInfo], limits: ArchiveLimits) -> None:
+    """The sizes the headers declare (`file_size`, `compress_size`), checked before any entry is
+    opened: a declared size over a limit is `too_large` without reading a byte. The declared
+    sizes are not trusted for the opposite case; `_read_entry` counts the real bytes."""
+    declared = 0
+    for info in entries:
+        if info.file_size > limits.max_file or info.compress_size > limits.max_compressed:
+            raise ArchiveError("too_large", info.filename)
+        declared += info.file_size
+        if declared > limits.max_uncompressed:
+            raise ArchiveError("too_large", "declared uncompressed size over the limit")
+
+
+def _read_entry(archive: zipfile.ZipFile, info: zipfile.ZipInfo, limits: ArchiveLimits, total: int) -> tuple[bytes, int]:
+    """Reads one entry in chunks and counts the real decompressed bytes: `too_large` is raised the
+    moment the entry or the running total exceeds its limit, before `zipfile` reaches the CRC check.
+    `zipfile` never yields more than the declared size, so a header that understates the size ends
+    in a size or CRC mismatch, which is `bad_zip`."""
+    chunks: list[bytes] = []
+    size = 0
+    try:
+        with archive.open(info) as handle:
+            while True:
+                chunk = handle.read(_CHUNK)
+                if not chunk:
+                    break
+                size += len(chunk)
+                total += len(chunk)
+                if size > limits.max_file or total > limits.max_uncompressed:
+                    raise ArchiveError("too_large", info.filename)
+                chunks.append(chunk)
+    except ArchiveError:
+        raise  # an `ArchiveError` is a `ValueError`: keep `too_large` out of the corrupt-stream clause below
+    except (zipfile.BadZipFile, RuntimeError, EOFError, ValueError, OSError, zlib.error, lzma.LZMAError) as exc:
+        # A corrupt stream surfaces as `zlib.error` (deflate), `OSError` (bzip2) or `LZMAError`, and an
+        # unsupported method as `NotImplementedError` (a `RuntimeError`): all are `bad_zip`, the one code callers catch.
+        raise ArchiveError("bad_zip", info.filename) from exc
+    return b"".join(chunks), total

spellwarden_scan/canonical.py

@@ -0,0 +1,16 @@
+"""The canonical package hash (spec 5.5): SHA-256 over `path NUL content NUL`
+for every path in byte-wise sorted order."""
+from __future__ import annotations
+
+import hashlib
+from collections.abc import Mapping
+
+
+def canonical_sha256(files: Mapping[str, bytes]) -> str:
+    digest = hashlib.sha256()
+    for path in sorted(files, key=lambda p: p.encode("utf-8")):
+        digest.update(path.encode("utf-8"))
+        digest.update(b"\x00")
+        digest.update(files[path])
+        digest.update(b"\x00")
+    return digest.hexdigest()