stacksmith-release
Warn
Audited by Snyk on Apr 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly invokes GH CLI commands (e.g., gh pr view, gh pr checks, gh run list/watch) to fetch Pull Request metadata, CI/deploy logs and statuses from GitHub (user-generated, public content) and uses those results to decide whether to merge, wait, or revert, and it also may curl a production URL extracted from CLAUDE.md — all of which the workflow (SKILL.md) treats as input that directly controls actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata