recipe-fit-assessor
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads only first-party catalog files and the user's stated goal, but the optional "Reference links / moodboards" input implies the agent may open arbitrary user-supplied URLs to clarify genre fit, which is a selected-URL fetch of outsider-authored content (low under the recall-first override).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata