wiki-self-heal
Warn
Audited by Snyk on Apr 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill explicitly performs web research using WebSearch/WebFetch and optional MCPs (Exa, Firecrawl, Apify) as part of its mandatory Research phase (see SKILL.md "Research tool selection" and references/loop.md step 9), fetching and ingesting public third‑party webpages to generate and apply wiki content, so untrusted web content can directly influence agent decisions and edits.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata