web-search-andi
Warn
Audited by Snyk on Jul 2, 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). The skill’s runtime “Search” capability calls a web search API (
/v1/search) with optionalextracts/metadata, which typically fetches and ingests third-party web page text (outsider-authored) into the LLM context as search results/snippets.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata