checkit
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime pipeline explicitly performs “Deep research” by fetching external web pages/articles/threads (outsider-authored free text) and then “Analyze the sources”/“Document the finding,” so the LLM context is fed outsider prose via the external URL fetch path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata