kandinsky

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches model reference documentation from a specified URL (https://www.pixazo.ai/models/kandinsky.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 (medium risk: 0.30). The skill instructs the agent to fetch external model reference documentation from https://www.pixazo.ai/models/kandinsky.md, which governs its behavior and configuration, constituting an operational dependency from an unofficial publisher.