curate-report
Warn
Audited by Snyk on Jul 30, 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 Step 3–4, the workflow uses GitHub MCP to list all comments on the triggering PR and then interprets the reviewer comments’ free-form natural language to classify REJECT/UPDATE/UNRESOLVED actions at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata