build-context
Warn
Audited by Snyk on Aug 14, 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’s runtime path (“Gather context”) instructs scanning conversation history and checking user-provided memory/notes/files, which are outsider-authored free text inputs consumed to draft the term list and final CONTEXT.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata