wan

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and ingests reference documentation from https://www.pixazo.ai/models/wan.md, which is an external URL/web page containing untrusted content.

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 model reference instructions from https://www.pixazo.ai/models/wan.md during runtime, constituting an unverifiable external runtime dependency with unknown provenance.