flowstudio-power-automate-debug

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls the FlowStudio MCP API (e.g., Step 5: mcp "get_live_flow_run_action_outputs" and related calls) to fetch action outputs and HTTP response bodies (outputs.body) — untrusted/user-generated content — and then uses those results to decide fixes and call update_live_flow/resubmit_live_flow_run, so third‑party content can directly influence agent actions.