tavily-research
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill calls Tavily’s Research API at runtime, which fetches and synthesizes public web pages into the returned
report/sources[].content, so outsider-authored free text from the web is ingested into the agent’s LLM context via the API response.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata