fetch-pr-feedback
Warn
Audited by Snyk on May 18, 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 explicitly fetches user-generated review and issue comments from GitHub via
gh apicalls to repos/$OWNER/$REPO/issues/$PR_NUMBER/comments and repos/$OWNER/$REPO/pulls/$PR_NUMBER/comments and then feeds the formatted comments into thebeagle-core:receive-feedbackverify→evaluate→execute loop, meaning untrusted third-party PR comments can be read and can materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata