web-search
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). This skill’s required workflow delegates to the
web-browsing/web-searchprotocol and will therefore likely ingest public web page text/snippets fetched at runtime (outsider-authored free text) into the agent’s LLM context for summarization/analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata