search

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

• Third-party content exposure detected (high risk: 0.90). The skill calls Tavily's web search API (POSTs to https://api.tavily.com/search and via https://mcp.tavily.com/mcp) and returns extracted text snippets or full page content (include_raw_content) from arbitrary public websites, so the agent ingests untrusted third‑party web content that could carry indirect prompt injections.