help

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly references and routes to external-research agents and MCP servers that fetch public web content—e.g., "oracle" and "pathfinder" (External research), and MCP servers like "firecrawl (Web scraping)", "github-search", and "perplexity"—which would ingest untrusted, user-generated or public web content for the agent to read and interpret.