alibabacloud-devops

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill shows and encourages passing the access token directly on the command line (--env YUNXIAO_ACCESS_TOKEN=your-token), which requires embedding a secret verbatim in commands and is an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). 该 Skill 的运行路径通过 MCP 工具直接读取云效/组织/代码管理/变更请求/流水线运行日志等内容（如 get_file_blobs、get_change_request、list_change_request_comments、get_pipeline_job_run_log），这些字段都可能包含由外部用户在云效里提交的自由文本且在工作流中被 LLM 读取。

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

• Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly invokes npx to fetch and execute remote npm packages at runtime (e.g., "npx -y alibabacloud-devops-mcp-server"), so it will download and run external code that the skill depends on.