pathml

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow validates user-supplied CSV slide manifests and cell tables where outsider-authored free text could be present.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill documentation mentions a Hugging Face URL (https://huggingface.co/pathml/test/resolve/main/mesmer.onnx) downloaded during runtime instruction when instantiating SegmentMIFRemote, constituting an unofficial operational external dependency.