tavily-remote-mcp

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md and accompanying scripts (notably tavily_search, tavily_extract, tavily_crawl and tavily_research) explicitly fetch and ingest open web content and arbitrary URLs (search results, page extractions, and crawls), so untrusted third‑party/user‑generated content can be read and materially influence agent behavior.