pr-review-canvas
Warn
Audited by Snyk on Aug 19, 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). In SKILL.md step 1, the workflow fetches GitHub PR free text directly from outsider-authored fields (PR title/body, file patches, and PR comment bodies) via
gh api repos/{owner}/{repo}/pulls/{number},/files, and/comments, then in step 2 it reads those diffs to generate HTML.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata