ai-wiki
Warn
Audited by Snyk on Aug 21, 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). SKILL.md’s required workflow can ingest outsider-authored free text via the “Web save” path that fetches user-pointed web pages (including repos) using
claude-defuddle, then routes/saves the extracted content into<AI_WIKI>without requiring the user to preselect a specific trusted item beyond the URL.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata