elevenlabs-voice-isolator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and process arbitrary external audio files via public URLs (e.g., "https://noisy-recording.mp3" in Quick Start and the Clean → Transcribe workflow), so untrusted user-provided audio can be transcribed/used and thus could contain instructions that influence downstream actions.

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

• Potentially malicious external URL detected (high risk: 0.80). This skill invokes the inference.sh platform via the belt CLI at runtime (e.g., "belt app run elevenlabs/voice-isolator") which contacts https://inference.sh to fetch and execute remote app code (the README even links to https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md), so it relies on externally-hosted code that is executed at runtime.