tavily-search
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires using the tavily-search and tavily-crawl CLI to fetch and crawl public web pages and URLs (see "执行流程" Step 1–3 and the command examples), then mandates the agent to read and interpret the returned web/search content ("Step 4 — 解读结果") — i.e., ingesting untrusted third-party web content that can influence subsequent summaries/actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata