mai-image

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to optionally fetch model documentation from a URL (https://www.pixazo.ai/models/mai-image.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 documentation (https://www.pixazo.ai/models/mai-image.md) at runtime to obtain parameter names and operational configurations, constituting an unverifiable third-party operational dependency under weak/unknown provenance.