huawei-cloud-modelarts-vllm-ascend-model-deploy@1.0.3
CAUTION· static onlyPublisher claims: "指导在华为云 ModelArts 推理平台通过 vLLM-Ascend 推理框架部署开源大语言模型(GLM/Qwen/DeepSeek/Llama 等)为昇腾 NPU 在线推理服务的完整流程。覆盖:确认模型后按 vllm-ascend 社区文档与用户确认部署形式(单机部署/多机部署/PD分离部署 3 种形式,统一单部署单元承载),从 HuggingFace/ModelScope 下载模型权重并上传 OBS、从 Quay.io 拉取 vllm-ascend 镜像并推送 SWR、按确认的部署形式选用专用脚本模板(单机/多机/PD 三套,脚本内不做部署形式运行时分支)生成启动/探针/角色识别脚本并上传 OBS、按 ModelArts 平台适配要点(端口 8080、OBS 挂载、bash 数组、探针命令检查、超节点亲和组)通过新版在线服务部署(二选一: 方式A 调用 CreateInferService API(POST /v2/{project_id}/services)自动部署 / 方式B 在 ModelArts 控制台按一步步点击指导手动部署;不再创建 AI 应用——该模块已废弃)、通过 OpenAI 兼容 API 调用验证。Triggers include: "ModelArts 部署大模型/开源模型", "vllm-ascend", "昇腾 NPU 推理", "HuggingFace/ModelScope 模型上云", "OBS/SWR 镜像迁移", "大模型在线服务", "多机部署", "多副本部署", "PD 分离部署", "超节点亲和组", "新版在线服务", "CreateInferService", "控制台手动部署在线服务"。当用户提到以上任一场景时都应使用本技能,即使没有明确说出'部署'二字。" Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-09 and scored it 52/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive file system command detected; Privileged sudo command. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
rm -f /tmp/pull_"$$.log"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.rm -f /tmp/push_"$$.log"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.d. sudo systemctl restart dockerFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo python3 fix_ub_endpoint.py # 先预览计划Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…d` 第 3 节);单实例(TP=1 且 DP=1)不复制 `get_master_ip.py`/`a5_hixlep/`(脚本内调用被条件包裹跳过);执行 `chmod +x` 赋予执行权限。**⚠️ LF 行尾强制(必做,违反=bash 无法执行)**: 产物与模板必须以 **LF 行尾**保存/上传——Windows 编辑/…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.c. sudo systemctl daemon-reloadFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.r = subprocess.run(["bash", "-n", f], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sudo python3 fix_ub_endpoint.py -y # 确认执行Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.跳过隐藏目录/文件(以 . 开头,如 .cac/、.env、.gitignore)与Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"请执行: chmod 600 {path}")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
28 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim huaweicloudskill: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.