git-toolkit
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill repeatedly fetches and interprets user-generated GitHub content (e.g., pr-description-sync Step 1: "gh pr view ... --json ... body" to read PR bodies, pr-checks-summary fetching CI run logs via
gh run view <run-id> --log-failed, and pr-conversation-resolve reading review threads via GraphQLreviewThreads) and uses those external, untrusted texts to decide verdicts, draft responses, and pick follow-up commands—so untrusted third-party content can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata