Search SOP
Warn
Audited by Snyk on Jul 17, 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). SKILL.md requires using
web_fetch(Layer 1.5) to directly access “any publicly accessible academic URL” and/or thebrowsertool (Layer 2) to open user-specified databases, which can ingest outsider-authored free text from fetched/scraped web pages into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata