Artifact Contract Auditor

Name/description match behavior: the script reads UNITS.csv and PIPELINE.lock.md, resolves a pipeline spec, checks for missing DONE outputs and pipeline target artifacts, and writes output/CONTRACT_REPORT.md. Declared requirements (python3/python) align with the provided Python scripts and modules. No unrelated credentials, binaries, or installs are requested.

SKILL.md restricts the skill to analysis-only and no network; the implementation matches that (reads workspace files and repo pipeline specs, writes the report and quality gate). One thing to note: the script resolves the pipeline path from the workspace's PIPELINE.lock.md and then uses Path(...).resolve() to load that file. If PIPELINE.lock.md points to an absolute path, the auditor will attempt to load that path — i.e., it will read whatever file path is specified. This is coherent for legitimate pipeline use, but it means the auditor can be directed to read arbitrary local files if the workspace's PIPELINE.lock.md is manipulated.

No install spec (instruction-only) and bundled Python code is executed directly; no downloads or external installers are used. This is the lowest-risk install model for bundled code, assuming the user trusts the packaged files.

The skill requests no environment variables or credentials. It only reads local workspace files and bundled pipeline specs. No secrets/external tokens are required or declared.

always:false and normal model-invocation settings. The skill writes only workspace-local report files (output/CONTRACT_REPORT.md and may update output/QUALITY_GATE.md via the quality_gate helper). It does not modify other skills or global agent configuration.