clawflows

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts and processes external HTTP/webhook triggers (POST /api/triggers/{flow-id}), integrates with external APIs and maps their JSON outputs (e.g., {"input_mapping": {"var1": "$.output.data"}}), and uses those inputs to drive conditional steps, which means untrusted third-party content from webhooks/APIs can be ingested and influence workflow actions.