review-pr
Warn
Audited by Snyk on Jul 16, 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 uses
gh pr view <PR> ... --jq ... -- bodyand step 4/5 instructs using the PR body and diff, which are outsider-authored GitHub PR content (author not the operating user) that becomes readable LLM context via the agent’s tool output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata