Workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill's run.sh and data-flow/components (e.g., the webhook-router in components/triggers and the fetch-url node) explicitly ingest external HTTP/webhook payloads and perform curl GET/POSTs to arbitrary third-party APIs (e.g., writing webhook body to workflows/flows/$WORKFLOW/data/00-trigger.json and fetching https://api.example.com/items), so untrusted user-generated web content is read and can directly influence workflow actions.