bmad-review
Warn
Audited by Snyk on Nov 13, 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). The skill reviews user-named content (a diff, branch, PR, ticket, or file), and that content can include outsider-authored text such as PR code comments, commit messages in the claims file, and ticket descriptions, which the Execution step 2 loader and the edge-case lens's claims check read at runtime; because the rules treat any GitHub PR reading as medium and the recall-first override applies, I score it medium even though the user selects the item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata