tavily
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly instructs the agent to use the Membrane CLI to query Tavily (an AI search engine) and to run proxied requests or "search"/"article" actions that ingest public web content and search results from Tavily's API, which are untrusted third‑party sources the agent would read and act on.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata