tavily-web-search

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls the Tavily web-search API (https://api.tavily.com/search) to fetch and synthesize real-time search results from public websites, and the SKILL.md instructs agents to parse/summarize those third-party results as part of their workflow, which allows untrusted external content to influence agent decisions.