external-mindstudio-msmodelslim-model-analysis

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md requires the agent to download and read files from public model repositories (e.g., the explicit modelscope download --model <org>/<model> ... step) and to parse repo-provided config.json and modeling_*.py, which are untrusted third‑party/user-generated content that the agent must interpret and which can materially influence analysis and subsequent actions.