web-search

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the skill calling web search and extract apps (e.g., belt app run tavily/extract with arbitrary "urls" and exa/extract and tavily/search-assistant) which fetch and ingest public web pages and search results from the open internet, so untrusted third-party content can be read and influence the agent's decisions.