meta-competitive-intel

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

• Third-party content exposure detected (high risk: 0.90). The runtime path uses the bundled multi-search-engine → web_research steps to fetch public web content and ingest the resulting page text/snippets into the agent’s LLM context for classification and summarization, which is outsider-authored free text from the public web.