tavily-search-free

Warn

Audited by Snyk on Jul 9, 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). SKILL.md describes a runtime web search via the Tavily Search API (“pi 会自动调用此技能进行网络搜索”), which will fetch public web pages and ingest their readable text (e.g., result content summaries) into the agent’s LLM context, creating an outsider-authored free-text injection surface.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 9, 2026, 01:11 PM
Issues
1
Security Audit — snyk — tavily-search-free