testing-parity

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly instructs reading external model checkpoints/configs (e.g., using safetensors.safe_open to load checkpoint metadata and Diffusers' MyModel.from_pretrained which pulls from the Hugging Face model hub / ~/.cache/huggingface), so it ingests public, user-published model/config data that is then parsed and used to drive debugging decisions.