flux

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 an external documentation page from https://www.pixazo.ai/models/flux.md, which is an arbitrary web page containing outsider-accessible or service-published content fetched at runtime.

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 instructions and reference data from https://www.pixazo.ai/models/flux.md at runtime, creating an unauthenticated third-party operational dependency with unknown publisher provenance.