gfpgan

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves fetching a documentation file from https://www.pixazo.ai/models/gfpgan.md, which is an optional/on-demand reference fetch rather than automatic monitoring of outsider-submitted content, representing a low risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching external markdown documentation from https://www.pixazo.ai/models/gfpgan.md to govern agent behavior, representing an unverified runtime external dependency from an unofficial publisher.