lambda

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

• Third-party content exposure detected (high risk: 0.70). The skill includes Lambda handlers that read and process untrusted request payloads (e.g., API Gateway event body in "handler(event, context)" and SQS message bodies in the "SQS Events" section), so the agent would ingest arbitrary third-party/user-provided content as part of its workflow.