external-mindstudio-document-ux-review

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly accepts arbitrary Git repository URLs and is designed to clone/read and follow README and directly linked docs (see SKILL.md "输入通常是一个 Git 仓库链接" and instructions "严格按文档走" / README example prompts with public repo URLs), so it ingests untrusted, user-generated third‑party content whose instructions can influence execution.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly takes git repository URLs as runtime inputs (for example https://gitcode.com/Ascend/msmonitor and the example https://github.com/example/project) and instructs the agent to fetch and follow the repo's README and linked docs step-by-step, meaning remote repository content will be retrieved at runtime and directly controls the agent's prompts/instructions and execution flow.