web-search
Warn
Audited by Snyk on Apr 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly calls out Tavily/Exa extract and search apps (e.g.,
infsh app run tavily/extract --input '{"urls": ["https://example.com/article1"]}'and the "Workflow: Extract + Summarize" that feeds extracted web page content into an LLM), which fetches and ingests arbitrary public web pages whose untrusted/user-generated content can influence downstream agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata