elevenlabs-dubbing

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and process arbitrary public audio/video URLs (e.g., "audio": "https://english-video.mp4", "https://podcast-episode.mp3") and then transcribe/dub and pass transcripts to downstream tools (STT/captioning), so untrusted, user-generated third‑party content is ingested and can materially influence outputs and subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes the inference.sh platform (https://inference.sh and related cloud.inference.sh) via the runtime command "infsh app run elevenlabs/dubbing", which fetches and executes remote app code hosted on that domain and is therefore a required external dependency that controls execution.