release-ci
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a contribution gate architecture where a gate check verdict is determined by the pull request body.
- Ingestion points: Pull request body text (referenced in
no-mistakes-required.yml). - Boundary markers: No specific delimiters or safety instructions are mentioned for separating the PR body content from the enforcement logic.
- Capability inventory: The workflow has the capability to enforce merge gates and run validation scripts (
pnpm test) based on the assessment. - Sanitization: The instructions do not specify how the LLM or gate logic filters instructions embedded within the PR body.
- [EXTERNAL_DOWNLOADS]: The CI workflow delegates enforcement to the
kunchenguid/no-mistakescomposite action. This is a vendor-owned resource associated with the skill author.
Audit Metadata