flowstudio-power-automate-debug

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The helper code and examples set MCP_TOKEN = "<YOUR_JWT_TOKEN>" and use it directly in request headers (x-api-key), which encourages embedding a JWT/API secret verbatim into generated code or commands and thus risks secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 4 and related examples) calls get_live_flow_run_action_outputs and explicitly instructs the agent to read outputs.body and inputs (HTTP response bodies and run payloads) — which can contain arbitrary, untrusted third-party or user-generated content from external APIs or users and is used to decide fixes and follow-up actions.