libtv-advanced

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

• Third-party content exposure detected (high risk: 0.90). The skill repeatedly queries the LibTV backend (scripts/libtv_workflow.py → libtv_client.query_session against im.liblib.tv), JSON-parses and displays backend/user-provided message content and extracts arbitrary media URLs from those messages which it then automatically downloads and uses for editing, so untrusted third‑party responses can directly influence tool actions.