md-review
Warn
Audited by Snyk on Jul 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill reads
feedback.jsonfrom the filesystem after a human reviewer exports it in the browser (outsider-authored free text in thecomments[].commentfields), via the runtime “Read feedback.json” step in Step 4.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata