z-image

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches external documentation from https://www.pixazo.ai/models/z-image.md on demand, which is low-risk user/external-fetched content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes API calls to an external service and instructs the agent to fetch external documentation (https://www.pixazo.ai/models/z-image.md), representing an inbound operational dependency on an unrecognized third-party service.