elevenlabs-stt

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate speech-to-text guide, but its install pointers send the user to an unpinned raw GitHub script from a differently named "belt-sh" namespace, which is sketchy without clear evidence of malicious intent.

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

• Third-party content exposure detected (low risk: 0.10). The workflow transcribes a user-supplied or arbitrary audio URL via belt app run elevenlabs/stt, so outsider-authored spoken content enters the agent's context only after the agent fetches a specific item, which is a low-risk path.