hidream

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 an arbitrary URL via instructions, which involves 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 documentation from https://www.pixazo.ai/models/hidream.md to govern its behavior, which constitutes an unverifiable runtime operational dependency on a third-party source.