genflare

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches model documentation from https://www.pixazo.ai/models/genflare.md and polls a third-party generation API (gateway.pixazo.ai). Because fetching documentation from a selected URL is a low-risk active fetch and the generation API processes user/system prompts rather than unselected outsider feeds, there is no automatic medium-risk injection path.

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 and documentation from https://www.pixazo.ai/models/genflare.md at runtime to govern its behavior and parameters, representing an unverified third-party operational dependency.