design-review
Warn
Audited by Snyk on Aug 23, 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
design-review(required workflowreferences/review-procedure.mdPart 2), the agent ingests outsider-authored free text at runtime via theJe reproduisline (including a[sector: {url}]register signal) which is read and used for present/absent and verdict branching before the challenger gate.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata