media-probe-api

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 specified in the reference section (https://www.pixazo.ai/models/media-probe-api.md), which is outside-accessible content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching external behavior-selecting documentation and executing an untrusted package installation command from an unverified third-party repository (Pixazo-AI/skills), presenting high-risk operational dependencies.