mmaudio

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

• Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to fetch a remote reference document from https://www.pixazo.ai/models/mmaudio.md, which exposes the agent to arbitrary content from a fetched URL.

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 configuration from https://www.pixazo.ai/models/mmaudio.md, representing an operational dependency on a third-party domain without established strong provenance.