audit-performance

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can be ingested via the runtime calls to public web sources in CallMcpTool(server: "user-firecrawl", toolName: "firecrawl_search"/"firecrawl_scrape", sources: [{ "type": "web" }]), which fetches and scrapes arbitrary web pages and returns their markdown into the agent’s LLM context (indirect prompt-injection risk).