babysitting-pr
Warn
Audited by Snyk on Jul 12, 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). This skill’s required workflow fetches and inspects outsider-authored PR review comments and inline comments via
gh pr view ... --json reviewDecision,reviews,commentsandgh api .../pulls/{pr}/comments --paginate, which are then read into the agent’s LLM context as free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata