lyria

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 a specified URL (https://www.pixazo.ai/models/lyria.md), which constitutes low-risk ingestion of external web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external model documentation and behavior-governing instructions from https://www.pixazo.ai/models/lyria.md, which is an unauthenticated, third-party operational dependency outside verified first-party publisher controls, presenting a high security risk.