input-configurations

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

• Third-party content exposure detected (high risk: 0.90). The skill's guides (notably references/httpjson-guide.md) require templates that fetch from arbitrary external URLs and message sources (request.url / SQS/S3/GCS/EventHub/Pub/Sub/webhook bodies) and explicitly use fields like .last_response.body.meta.next_cursor and response.pagination to build subsequent requests and cursor state, so untrusted third‑party responses can directly influence the agent's next actions.