web-research
Warn
Audited by Snyk on Apr 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill programmatically runs web searches and (optionally) full-page fetches from arbitrary public webpages—see SKILL.md's requirement to verify WebSearch/WebFetch and references/subagent-brief.md and citation-schema.md which require subagents to ingest page URLs and verbatim excerpts into findings—so untrusted third-party content is read and used to drive synthesis and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata