babysit-pr
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md Step 1/2 uses GitHub CLI commands (
gh pr view,gh pr checks,gh pr diff,gh run view --log-failed) to ingest PR content and CI log text authored by an external party (the PR contributor and the CI system), which then becomes readable prose in the agent/LLM runtime context for reasoning.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata