extract-wisdom

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads arbitrary web pages via wisdom.py fetch and YouTube transcripts, which can contain outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes transcribe.py which retrieves a remote GitHub repository (https://github.com/istupakov/onnx-asr.git) at runtime as an explicit PEP 723 skill dependency.