audit-db-schema

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses runtime web fetching via Firecrawl (CallMcpTool(server: "user-firecrawl", toolName: "firecrawl_search"/"firecrawl_scrape") with sources: [{ "type": "web" }]), which can ingest outsider-authored free-form page text into the agent’s LLM context for “Research Schema Best Practices.”