muse-voice

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches documentation from an arbitrary external URL (https://www.pixazo.ai/models/muse-voice.md), which exposes the agent to low-risk indirect prompt injection.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch instructions and schema documentation from https://www.pixazo.ai/models/muse-voice.md, an unrecognized third-party domain, constituting an unverified operational dependency under the dependency gate rules.