Skills/ClawHub/huawei-cloud-modelarts-vllm-ascend-model-deploy

huawei-cloud-modelarts-vllm-ascend-model-deploy@1.0.1

CAUTION

Publisher 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(单节点/多节点/PD分离/PD共置 4 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(单节点/多节点/PD/PD共置 四套,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、Mooncake KV 传输)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", "PD 共置部署", "超节点亲和组", "Mooncake KV 传输", "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.

Registry ClawHubPublisher huaweicloudskill · joined 12 days agoInstalls 247Last detonated 7d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-27 and scored it 54/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Outbound HTTP to raw IP address. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This 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

MEDIUM
Python subprocess execution detectedscripts/check_artifacts.py:93 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addressSKILL.md:433 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsscripts/upload_code_to_obs.py:66 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Outbound HTTP to raw IP addressSKILL.md:433 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandSKILL.md:302 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/create_infer_service.py:257 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:367 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

What would make this Verified

26 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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.
  2. 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.
  3. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim huaweicloudskill