tavily-search

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: 0.85). This skill calls Tavily’s public web search API at runtime and (optionally) ingests extracted page text (include_raw_content: trueresults[].content) from arbitrary third-party websites into the agent’s LLM context, which is outsider-authored free text.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 23, 2026, 06:06 AM
Issues
1
Security Audit — snyk — tavily-search