tavily-search

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests live web content via the Tavily Search API (see SKILL.md) and the runtime script scripts/search.py returns web results, snippets and an API-generated "answer" which the workflow requires the agent to read and use when forming responses, so untrusted third-party pages could indirectly inject instructions.