secure-code-agent 0.2.0__py3-none-any.whl

secure_code_agent-0.2.0.dist-info/METADATA

@@ -0,0 +1,328 @@
+Metadata-Version: 2.4
+Name: secure-code-agent
+Version: 0.2.0
+Summary: Deterministic security gate + bounded AI remediation prompt generator. NIST SSDF / OWASP ASVS / CWE Top 25 anchored.
+Author: Marshall Guillory
+License: MIT
+Project-URL: Homepage, https://github.com/marshallguillory86/secure-code-agent
+Project-URL: Repository, https://github.com/marshallguillory86/secure-code-agent
+Project-URL: Documentation, https://github.com/marshallguillory86/secure-code-agent/tree/main/docs
+Project-URL: Issues, https://github.com/marshallguillory86/secure-code-agent/issues
+Project-URL: Changelog, https://github.com/marshallguillory86/secure-code-agent/blob/main/CHANGELOG.md
+Keywords: security,appsec,sast,sca,secret-scanning,owasp,asvs,cwe,nist-ssdf,sarif,ai-code-review,ai-guardrail,remediation-prompt,ci,audit
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Security
+Classifier: Topic :: Software Development :: Quality Assurance
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Dynamic: license-file
+
+# secure-code-agent
+
+> **Deterministic security gate + bounded AI remediation prompts for repos with AI coding agents in the loop.**
+> Anchored to NIST SSDF · OWASP ASVS · OWASP Top 10 · MITRE CWE Top 25 · OpenSSF Scorecard · SARIF 2.1.0.
+
+```bash
+pip install secure-code-agent
+
+secure-code-agent --fail-on-gate \
+    --output secure-code-report.md \
+    --prompt-output secure-code-remediation-prompt.md \
+    --sarif-output secure-code.sarif
+```
+
+The sibling of [`maintainability-agent`](https://github.com/marshallguillory86/maintainability-agent). Same shape: deterministic CI gate · plain-file outputs · per-host skill bundle. Different concern: security, not maintainability.
+
+---
+
+## Why this exists
+
+AI coding agents ship code at human-review-saturating speed. Point them at a security finding and the documented anti-patterns are:
+
+| Anti-pattern                                       | What the agent actually does                                                                       |
+|----------------------------------------------------|----------------------------------------------------------------------------------------------------|
+| **Crypto roulette**                                | "Replace MD5 with SHA-256" → rewrites the hashing module to use a library it saw in training data.|
+| **Auth-flow rewrite**                              | "Fix the IDOR" → refactors the session model. Now you have an unaudited new auth path.            |
+| **Validation softening**                           | "Make the tests pass after the fix" → weakens the regex / removes the bounds check.               |
+| **Test deletion**                                  | "The security test is failing" → deletes the test.                                                 |
+| **Lint disable**                                   | "This rule fires repeatedly" → `# nosec`, `# noqa`, `eslint-disable` everywhere.                  |
+| **Scope creep**                                    | "I fixed the SQLi" → followed by 600 lines of unrelated refactoring.                              |
+| **Dependency thrash**                              | "Bumping the vulnerable package" → introduces 12 unrelated new dependencies.                       |
+| **Silent behavior change**                         | "It works now" → same input, different output. Downstream callers break.                          |
+
+Existing scanners (Semgrep, Bandit, CodeQL, Snyk, Trivy) emit findings. None of them ship a **bounded prompt back to the agent** that says *"fix only these specific findings, do not touch crypto/auth/validation/logging, preserve behavior."*
+
+That gap is what this tool fills.
+
+## The output that matters
+
+Every other security scanner stops at "here's a list of findings." `secure-code-agent` generates a remediation prompt:
+
+```markdown
+# Security remediation — bounded scope
+
+You are fixing the security findings listed in §FINDINGS below.
+This is a constrained task, not a refactor.
+
+## Hard constraints (MUST NOT violate)
+
+1. Fix only the findings listed in §FINDINGS. Do not touch unrelated
+   code, files, or modules.
+2. Do not change cryptographic algorithms, key derivation, IV/nonce
+   handling, padding modes, or random sources unless a finding in
+   §FINDINGS explicitly names them as the defect.
+3. Do not change authentication flows, session handling, token
+   lifetime, cookie attributes, or authorization gates unless a
+   finding in §FINDINGS explicitly names them.
+4. Do not weaken input validation, output encoding, sanitization,
+   bounds checks, regex strictness, or rate limits to make existing
+   tests pass.
+5. Do not disable, delete, or skip security tests. Do not remove
+   `@_limiter.limit`, `@require_auth`, `@require_csrf`, or similar
+   decorators.
+6. Do not silence linter warnings via `# nosec`, `# noqa`, `# type:
+   ignore`, `eslint-disable`, `sonar-disable`, or equivalent.
+7. Do not introduce new third-party dependencies. Prefer stdlib or
+   already-vendored libraries.
+8. Preserve behavior. Same inputs must produce the same outputs
+   unless a finding explicitly proves the current behavior is unsafe.
+9. Add a focused test that exercises the specific security boundary
+   you fixed. The test must FAIL on the pre-fix code and PASS on
+   the post-fix code. No "TODO: add test later".
+10. Keep the patch small. If you find yourself rewriting a function
+    rather than patching it, stop and report the structural issue.
+
+## §FINDINGS
+...
+```
+
+Hand the prompt to Claude Code, Codex, Cursor, Copilot, or any agent. The agent now has explicit boundaries. The full template + rationale lives in [`docs/remediation.md`](docs/remediation.md).
+
+## Standards anchored, not invented
+
+Every finding maps to five public standards. Operators see *which standard is failing*, not just *which scanner shouted*.
+
+| Source                                       | What we use it for                                       |
+|----------------------------------------------|----------------------------------------------------------|
+| [NIST SSDF SP 800-218](https://csrc.nist.gov/pubs/sp/800/218/final) | Process practice id (e.g. `PW.5.1`) |
+| [OWASP Top 10 (2021)](https://owasp.org/Top10/2021/) | Risk bucket (e.g. `A03:2021-Injection`) |
+| [OWASP ASVS 5.0](https://github.com/OWASP/ASVS) | Verification requirement (e.g. `V5.3`) |
+| [MITRE CWE Top 25 (2025)](https://cwe.mitre.org/top25/) | Canonical weakness id — the dedupe key |
+| [OpenSSF Scorecard](https://openssf.org/projects/scorecard/) | Repo + supply-chain hygiene |
+| [SARIF 2.1.0](https://www.oasis-open.org/standard/sarif-v2-1-0/) | Output format (and external scanner ingest) |
+
+When Semgrep, CodeQL, and Bandit fire on the same SQL-injection sink with three different rule ids, they all map to `CWE-89` and the scorer counts **one** underlying weakness. Not three.
+
+## Architecture (orchestrator, not engine)
+
+```text
+┌────────────────────────────────────────────────────────────────────┐
+│  secure-code-agent CLI                                              │
+│                                                                     │
+│  Config → Scanners (subprocess) → Findings → Scoring → Renderers   │
+│                                                                     │
+│                                            ┌──────────────────┐    │
+│                                            │ Markdown report  │    │
+│                                            │ JSON             │    │
+│                                            │ SARIF 2.1.0      │    │
+│                                            │ PR comment       │    │
+│                                            │ Remediation 🪄    │    │
+│                                            │ Agent standards  │    │
+│                                            └──────────────────┘    │
+└────────────────────────────────────────────────────────────────────┘
+        │
+        │   Scanners (subprocess, version-isolated):
+        │
+        ├── Bandit            (Python SAST)
+        ├── Semgrep           (multi-language SAST + SARIF ingest)
+        ├── pip-audit         (Python SCA)
+        ├── npm audit         (Node SCA)
+        ├── Gitleaks          (secret scanning, history-aware)
+        ├── TruffleHog        (verified secret scanning)
+        ├── Trivy             (containers / IaC / k8s / vuln / secret)
+        ├── Checkov           (Terraform / CloudFormation / Helm / k8s)
+        ├── Hadolint          (Dockerfile lint)
+        ├── OSV-Scanner       (multi-ecosystem SCA via osv.dev)
+        ├── OpenSSF Scorecard (repo hygiene + supply chain)
+        ├── eslint-plugin-security  (JS/TS SAST)                     [v0.3]
+        ├── CodeQL SARIF      (ingest GitHub-hosted analysis)
+        └── Built-in regex rules (high-confidence, low-FP)
+```
+
+We don't reimplement SAST. We invoke best-in-class scanners as subprocesses, parse their canonical output, normalize across CWE/OWASP/ASVS/SSDF, and produce one ranked view.
+
+Full architecture in [`docs/design.md`](docs/design.md).
+
+## Audit categories (9 buckets, 1 grade)
+
+Findings roll up to nine canonical categories. The grade is driven by the **worst category** — one CRITICAL secret in git history shouldn't be offset by a clean dependency tree.
+
+| Category                | Examples                                                                        |
+|-------------------------|---------------------------------------------------------------------------------|
+| `secrets`               | Hardcoded API keys, tokens in history, `.env` committed                         |
+| `dependencies`          | CVE in pinned dep, yanked package, abandoned upstream                           |
+| `code_vulnerabilities`  | SQLi, XSS, command-injection, path-traversal, SSRF, XXE, deserialization        |
+| `auth_authz`            | Missing auth gate, IDOR, broken access control, JWT misuse                      |
+| `crypto`                | Weak alg, hardcoded IV, ECB, MD5/SHA-1 for security, missing constant-time      |
+| `supply_chain`          | Unpinned action, missing SBOM, no signed releases, low Scorecard                |
+| `config_iac`            | World-readable S3, public security group, Dockerfile `USER root`, k8s privileged|
+| `logging_observability` | Secrets in logs, PII in URLs, missing audit trail on auth events                |
+| `policy_docs`           | Missing SECURITY.md, no responsible-disclosure path, no threat model            |
+
+Scoring math + worked examples in [`docs/scoring.md`](docs/scoring.md).
+
+## Hard gates
+
+```json
+{
+  "gates": {
+    "fail_on_severity":    ["critical", "high"],
+    "fail_on_category":    ["secrets", "auth_authz"],
+    "fail_on_new":         true,
+    "min_score":           4.0,
+    "require_scanners":    ["bandit", "gitleaks"],
+    "max_unsuppressed":    { "critical": 0, "high": 0, "medium": 10 }
+  }
+}
+```
+
+Any tripped gate is a nonzero exit. Compose freely.
+
+## Suppressions you can't game
+
+`.scignore.yaml` — every suppression requires a `reason` AND an `expires` date (max 365 days). Past-expiry suppressions become CRITICAL findings on their own. You can't ship `reason: "we'll fix it later"` forever.
+
+```yaml
+- file: services/legacy_billing.py
+  rule_id: "*"
+  reason:  "Slated for rewrite Q3 2026 — gated by initiative INV-44."
+  expires: "2026-09-30"
+
+- rule_id: "B101"
+  paths:   ["tests/"]
+  reason:  "assert statements are legitimate in test code."
+  expires: "2027-05-13"
+```
+
+Wildcard rule (`rule_id: "*"`) requires a `file` or `paths` scope — you cannot disable a rule globally.
+
+## Baseline + incremental adoption
+
+`secure-code-baseline.json` fingerprints every current finding. On the next run:
+
+- Findings present in baseline → **acknowledged**; don't trip `fail_on_new`.
+- Findings missing from baseline → **new**; trip the gate.
+
+Bumping a CRITICAL or HIGH finding into the baseline requires `--bump-baseline --i-acknowledge-risk`. The bump records the operator's git `user.email` per fingerprint so PR review can see who acknowledged what.
+
+This lets legacy repos adopt the gate without a 200-finding day-one cleanup.
+
+## Quickstart
+
+```bash
+# Install
+pip install secure-code-agent
+
+# Initialize agent standards files for your AI coding tools
+secure-code-agent --init-agent-standards \
+    --target codex --target claude-code --target cursor --target copilot
+
+# Run an audit with hard-gate exit
+secure-code-agent --config secure-code-agent.json \
+    --fail-on-gate \
+    --output secure-code-report.md \
+    --json-output secure-code-report.json \
+    --sarif-output secure-code.sarif \
+    --comment-output secure-code-pr-comment.md \
+    --prompt-output secure-code-remediation-prompt.md
+
+# Audit only changed files since main
+secure-code-agent --changed-only main...HEAD --fail-on-new
+
+# Ingest external scanner SARIF (CodeQL, Snyk, Trivy, etc.)
+secure-code-agent --sarif-import codeql-results.sarif \
+                   --sarif-import snyk-results.sarif
+```
+
+## Invokable skill / slash command
+
+For agents that support invokable skills, this repo ships a portable skill under [`skills/secure-code-agent/`](skills/secure-code-agent/). The `SKILL.md` body is the source of truth; per-host adapters live under `agents/` and `copilot/`.
+
+| Host                      | Install destination                                                                 | Invocation                          |
+|---------------------------|-------------------------------------------------------------------------------------|-------------------------------------|
+| Codex / OpenAI            | wired via `skills/secure-code-agent/agents/openai.yaml`                             | per Codex's skills convention       |
+| Claude Code               | `cp -r skills/secure-code-agent ~/.claude/skills/`                                  | `/secure-code-agent`                |
+| GitHub Copilot (VS Code)  | `cp skills/secure-code-agent/copilot/secure-code-agent.prompt.md .github/prompts/`  | `/secure-code-agent` in Copilot Chat |
+
+## GitHub Action
+
+```yaml
+- uses: marshallguillory86/secure-code-agent@v0.1.0
+  with:
+    config: secure-code-agent.json
+    changed-only: main...HEAD
+    fail-on-gate: true
+```
+
+The action uploads SARIF to GitHub Code Scanning by default. See [`action.yml`](action.yml) and [`examples/github-actions/`](examples/github-actions/) for full workflows.
+
+## What this is NOT
+
+- ❌ **Not a SAST engine.** We delegate to Semgrep / Bandit / CodeQL / etc. — we don't write yet another AST analyzer.
+- ❌ **Not a runtime defense.** No WAF, no IDS, no agent in the request path. Static + supply-chain + config only.
+- ❌ **Not a SaaS.** Findings live as files in your repo. No telemetry. No version-check ping.
+- ❌ **Not a license scanner.** Pair with `pip-licenses` / `license-checker` separately.
+- ❌ **Not an exploit generator.** No DAST, no fuzzing.
+
+## Design principles
+
+1. **Deterministic first, AI optional.** The audit never calls an LLM by default. The remediation prompt is a generated artifact you choose to hand to an agent.
+2. **Bounded scope.** The remediation prompt explicitly forbids touching crypto, auth, validation, logging, and tests.
+3. **Standards-anchored.** Five public standards (NIST / OWASP-x3 / CWE) — no invented taxonomy.
+4. **CWE-deduped scoring.** One underlying weakness = one finding, regardless of how many scanners found it.
+5. **No vendor lock-in.** Markdown, JSON, SARIF, plain files. Pipe anywhere.
+6. **CI-first, local-first.** Same binary in pre-commit, local CI, GitHub Actions, GitLab, Buildkite.
+
+Full design philosophy in [`docs/design.md`](docs/design.md).
+
+## Documentation
+
+- [`docs/design.md`](docs/design.md)              — Architecture + non-goals + scanner protocol
+- [`docs/standards.md`](docs/standards.md)        — NIST SSDF / OWASP / CWE / Scorecard / SARIF citations
+- [`docs/scoring.md`](docs/scoring.md)            — Weighting model + worked examples
+- [`docs/scanners.md`](docs/scanners.md)          — Per-scanner integrations + caveats
+- [`docs/remediation.md`](docs/remediation.md)    — The prompt template + failure-mode rationale
+- [`docs/threat-model.md`](docs/threat-model.md)  — What we defend against (and what we don't)
+
+## Versioning
+
+- **Semver.** v0.x is pre-1.0 — the config schema may evolve. v1.0 locks it.
+- **SARIF 2.1.0** output is pinned and validated against the OASIS schema in CI.
+
+## Get in touch
+
+- Bug reports / feature requests — [GitHub Issues](https://github.com/marshallguillory86/secure-code-agent/issues)
+- Security vulnerabilities in this tool — see [`SECURITY.md`](SECURITY.md)
+
+## License
+
+MIT — see [`LICENSE`](LICENSE).
+
+---
+
+Built by [Marshall Guillory](https://github.com/marshallguillory86). The companion to [`maintainability-agent`](https://github.com/marshallguillory86/maintainability-agent) — both tools encode a single thesis: *AI agents need deterministic boundaries, not best-effort guardrails.*

secure_code_agent-0.2.0.dist-info/RECORD

@@ -0,0 +1,33 @@
+secure_code_agent-0.2.0.dist-info/licenses/LICENSE,sha256=SOAOD6SRucfO7P_MWSLyyjwgr7x0s1BDaIskdGU8idI,1074
+secure_code_audit/__init__.py,sha256=82fWpCgoLm2uJxiJXoUrCK1ntvHvng10lxjijdHByBk,113
+secure_code_audit/baseline.py,sha256=1W8UJ2z_MeOXQwzXNg3-oiKEMKNAGYHDT4O-678SGKo,3599
+secure_code_audit/cli.py,sha256=YSMnAZmn36UNkBGqQ3sVi_aqbX-t6_g4o9Cuy0FDrBI,10422
+secure_code_audit/config.py,sha256=vYrNHa7LgHO7a4iDsoy2nrYfBYOX2f1UOzkZXf5Ec3E,4552
+secure_code_audit/findings.py,sha256=mZ4FzAysoVVTal2GKK_WHZcIdQ6iZ7foYv3jyahqeHE,5847
+secure_code_audit/git_tools.py,sha256=hgpDlH0tpjL7FbMa8BNMjx7-Rput3OdonbtvX5lqGas,2826
+secure_code_audit/instructions.py,sha256=XnRp6GU3WgdVDDg4M6wfG4zWuN63G64adrxH_7DY6-Y,5710
+secure_code_audit/remediation.py,sha256=tmDLLAL4_lJIutHKqB5R3Hm64cdzHbc_UC0G3kFyOws,6404
+secure_code_audit/renderers.py,sha256=taw_OcLly0H-gIKo2fGGLIq6J-7orGe1WRI4PObP9kc,9694
+secure_code_audit/sarif.py,sha256=84YERJ0bpsJZFs-lue5YWJVHBbeEgfV_W9lfQ_MLNvQ,7529
+secure_code_audit/scoring.py,sha256=AzODfq06-cRX15EdXkVmZk3QtubFkymgr0NOtGzubwo,9393
+secure_code_audit/standards.py,sha256=S-mckmaEPsCWN2M7wjkL8vUnyI1TfcFffaQXDcRdzlw,21346
+secure_code_audit/suppressions.py,sha256=80-4gm0dZRcSpv3F9oNWbA2ASLIBqjJiFjvCq-bBKFw,6423
+secure_code_audit/scanners/__init__.py,sha256=a_EbP22p7pEID8GeZapE3qIChFFT1IQSUUpFoqBVJfI,2116
+secure_code_audit/scanners/bandit_scanner.py,sha256=bu24O0CSksNORult-qjaRVSL2aL-QUzvcl13qPNntcM,3275
+secure_code_audit/scanners/base.py,sha256=wDZXg8sk2YPnFygQHOJZnhb_xkHCVAAXgLWPzYLdmu0,7202
+secure_code_audit/scanners/builtin_rules.py,sha256=Ra8Jvw6BV2aKEPZEioBXMi8DIPcg-muax7yovPVTVaM,7106
+secure_code_audit/scanners/checkov_scanner.py,sha256=DWy4Z8WAuBLV8w8-BWbAxHO7PjtQSk3hvpNjtkEi0qo,2788
+secure_code_audit/scanners/gitleaks_scanner.py,sha256=nAEnNyjtqwBPw_QmRlaXVbVOQQEHPu220TU8hMoTakE,3526
+secure_code_audit/scanners/hadolint_scanner.py,sha256=Pu10qRkbQxMkZClmzBW1cNTafzZjAaiRXi3xQydgljs,4142
+secure_code_audit/scanners/npm_audit_scanner.py,sha256=As_VmmPiYX0tv_xM_FkIG8TfEctUoQkhaHeisrQ3_R8,4150
+secure_code_audit/scanners/osv_scanner.py,sha256=Juf2GQrPz_FbY9Fe7ulxar149PRg1f3P8lJLkkfk4X0,4182
+secure_code_audit/scanners/pip_audit_scanner.py,sha256=aIfc82QDT0R72dK83twy_kB6rhSkOsZn0nQo1CzE_8c,3373
+secure_code_audit/scanners/scorecard_scanner.py,sha256=_MfrtSIrZS0zF8JOuPNmdjS0OC0szz8jRUWfYBrIxRg,5690
+secure_code_audit/scanners/semgrep_scanner.py,sha256=SrFzSZjtaYEHzkSTWn674iAlyZI2X8RW3teIhler37w,4982
+secure_code_audit/scanners/trivy_scanner.py,sha256=nlLSSG7vUdDC5KfRZknyMO6GszzgSRWB4THPAw2oblo,3704
+secure_code_audit/scanners/trufflehog_scanner.py,sha256=-1M80Z0aQMHix9kx7ApO5HZZbhMQjhM0qPzIEWXbK3o,3397
+secure_code_agent-0.2.0.dist-info/METADATA,sha256=WBI37yNh-DMmBODZMJPv90ivF39mbKMuEemZpfQfvCg,18188
+secure_code_agent-0.2.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+secure_code_agent-0.2.0.dist-info/entry_points.txt,sha256=3UemK2tMwhHlnl0Gbq4FQxEwwiKlf5Lrid5a6djRTSQ,112
+secure_code_agent-0.2.0.dist-info/top_level.txt,sha256=GzzNIUU8eQ0h2_gStV7sPnK3CeoSGdVHXqVb1Nn0AVA,18
+secure_code_agent-0.2.0.dist-info/RECORD,,

secure_code_agent-0.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

secure_code_agent-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+secure-code-agent = secure_code_audit.cli:main
+secure-code-audit = secure_code_audit.cli:main

secure_code_agent-0.2.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Marshall Guillory
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

secure_code_agent-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+secure_code_audit

secure_code_audit/__init__.py

@@ -0,0 +1,3 @@
+"""secure-code-agent — deterministic security gate + bounded AI remediation prompts."""
+
+__version__ = "0.2.0"

secure_code_audit/baseline.py

@@ -0,0 +1,110 @@
+"""Baseline — incremental adoption.
+
+A baseline is a JSON file mapping `fingerprint → metadata` for findings the
+operator has acknowledged at a point in time. On the next run:
+
+  · fingerprint in baseline   → finding.is_new = False (acknowledged)
+  · fingerprint not in baseline → finding.is_new = True  (trips fail_on_new)
+"""
+from __future__ import annotations
+
+import datetime
+import json
+import subprocess
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Iterable
+
+from secure_code_audit.findings import Finding
+
+
+@dataclass(frozen=True)
+class BaselineEntry:
+    fingerprint:    str
+    rule_id:        str
+    severity:       str
+    category:       str
+    file_path:      str
+    first_seen:     str        # ISO 8601 UTC
+    bumped_by:      str        # git user.email when added
+    notes:          str = ""
+
+
+def load(path: Path) -> dict[str, BaselineEntry]:
+    if not path.exists():
+        return {}
+    try:
+        raw = json.loads(path.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return {}
+    entries: dict[str, BaselineEntry] = {}
+    for fp, body in (raw.get("entries") or {}).items():
+        entries[fp] = BaselineEntry(
+            fingerprint=fp,
+            rule_id    =body.get("rule_id", ""),
+            severity   =body.get("severity", ""),
+            category   =body.get("category", ""),
+            file_path  =body.get("file_path", ""),
+            first_seen =body.get("first_seen", ""),
+            bumped_by  =body.get("bumped_by", ""),
+            notes      =body.get("notes", ""),
+        )
+    return entries
+
+
+def write(path: Path, findings: Iterable[Finding], existing: dict[str, BaselineEntry]) -> None:
+    """Rewrite the baseline file. Existing entries' first_seen + bumped_by
+    are preserved so a baseline bump only mutates net-new entries."""
+    now_iso  = datetime.datetime.now(datetime.UTC).strftime("%Y-%m-%dT%H:%M:%SZ")
+    operator = _git_user_email()
+
+    entries: dict[str, dict] = {}
+    for f in findings:
+        if f.suppressed:
+            continue
+        prev = existing.get(f.fingerprint)
+        entries[f.fingerprint] = {
+            "rule_id":    f.rule_id,
+            "severity":   f.severity.value,
+            "category":   f.category.value,
+            "file_path":  f.file_path.as_posix(),
+            "first_seen": prev.first_seen if prev else now_iso,
+            "bumped_by":  prev.bumped_by  if prev else operator,
+            "notes":      prev.notes      if prev else "",
+        }
+
+    path.write_text(
+        json.dumps(
+            {
+                "version":  1,
+                "updated":  now_iso,
+                "operator": operator,
+                "entries":  entries,
+            },
+            indent=2,
+            sort_keys=True,
+        ),
+        encoding="utf-8",
+    )
+
+
+def mark_new(findings: list[Finding], baseline: dict[str, BaselineEntry]) -> list[Finding]:
+    """Set is_new=True on findings whose fingerprint is not in the baseline.
+    Returns a new list with mutated Finding objects (frozen dataclass →
+    replace)."""
+    from dataclasses import replace
+    out: list[Finding] = []
+    for f in findings:
+        out.append(replace(f, is_new=f.fingerprint not in baseline))
+    return out
+
+
+def _git_user_email() -> str:
+    try:
+        r = subprocess.run(
+            ["git", "config", "user.email"],
+            check=False, capture_output=True, text=True, timeout=5,
+        )
+        return r.stdout.strip() or "unknown"
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return "unknown"