iterate-pr
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 actively fetches and ingests untrusted, user-generated GitHub content (PR comments and review threads via scripts/fetch_pr_feedback.py using
gh api/GraphQL and CI logs via scripts/fetch_pr_checks.py usinggh run view --log-failed), and the workflow instructs the agent to read and act on that content to decide fixes and push changes, creating a clear avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata