debug-fe-be-integration

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

• Third-party content exposure detected (high risk: 0.85). This workflow calls web and other external MCP tools (e.g., Firecrawl with sources: [{ "type": "web" }] and Context7), whose fetched results are outsider-authored free-form text that would be ingested into the LLM context at runtime via CallMcpTool.