smart-resize

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external model documentation from a URL on demand, which is an active search/fetch action rather than automatic monitoring of untrusted incoming 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 instructions and documentation from an external URL (https://www.pixazo.ai/models/smart-resize.md), which constitutes an operational inbound dependency on a third-party source.