lucy-edit

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

• Third-party content exposure detected (low risk: 0.10). The agent fetches documentation from https://www.pixazo.ai/models/lucy-edit.md, which is a low-risk active fetch of external documentation.

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 instructions from https://www.pixazo.ai/models/lucy-edit.md at runtime to govern its behavior and resolve parameters, constituting an unverified operational dependency under a common unofficial publisher.