review-pr
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). At runtime the workflow runs
gh pr view $ARGUMENTS --json title,body,files,..., which ingests outsider-authored pull request metadata (e.g., the PR title/body and changed file contents) into the LLM for review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata