gemini-omni

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 fetch documentation from https://www.pixazo.ai/models/gemini-omni.md, which is an active fetch of vendor documentation/model reference rather than ingestion of unselected outsider-authored text.

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 markdown instructions from https://www.pixazo.ai/models/gemini-omni.md at runtime to govern its behavior, which constitutes an operational dependency with unknown/third-party provenance.