scribe

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-provided media via file URLs and S3 input (see Core Workflow step 3/5 and examples/batch-webhook-pipeline.md / examples/fast-mode-node.md) and then persists and post-processes the resulting transcripts, so untrusted user-generated content could influence downstream decisions or actions.