tavily
Warn
Audited by Snyk on Feb 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: 0.90). The TavilySearchTool calls TavilyClient.search in tavily_search.py to retrieve live web search results (titles, URLs, and result "content") from the open internet and then includes those untrusted, third‑party contents in quick_search/JSON outputs that Alice is expected to read.
Audit Metadata