web-search

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

• Third-party content exposure detected (high risk: 0.95). The required workflow uses runtime web/platform search APIs (e.g., Tavily/Exa/Valyu/SearchAPI) that fetch and return third-party page text (public web content, platform listings, comments/transcripts), which is then ingested into the agent’s LLM context as readable search results/citations—an outsider-authored free-text source.