heyeddi-ci-respond
Warn
Audited by Snyk on Aug 11, 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,
fetch_pr_commentscallsgh api repos/{repo}/pulls/{pr}/commentsandgh pr view ... --json {comments,reviews}, writes the returned PR commentbodytext into.heyeddi/docs/pr-<N>-ci-comments.json(wrapped as<<<UNTRUSTED_EXTERNAL_CONTENT>>>), and later pipeline steps ingest that cached free text for filtering and reply generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata