Skill 审计报告
serving-llms-on-epyc 审计报告.
Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda. Use for "vLLM on CPU", "zentorch serving", or an EPYC CPU endpoint, including on a host that also has AMD Instinct GPUs. Detects the EPYC generation, validates the runtime, checks model support and RAM fit, sizes threads/KV/NUMA, confirms the plan, launches, and verifies the endpoint. Runs one instance on one socket and its memory. Reports and stops on failure; does not retry or debug. Use serving-llms-on-instinct when the endpoint should run on a GPU. Excludes multi-node, EPYC 4000, and pre-Zen4 EPYC without AVX-512.
OpenAgentSkill 信任评分
OpenAgentSkill 信任评分
Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。
GitHub 采用度
信息62
332 个 GitHub Stars
Star/Fork 活跃度
警告57
332 个 Star，30 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过88
距上次推送 1 个月
许可证清晰度
通过86
MIT
README/SKILL.md 完整度
通过86
元数据包含足够的用法与工作流上下文
依赖与运行时风险
警告44
command execution surface, credential or environment access
安装可用性
通过92
npx skills add amd/skills --skill serving-llms-on-epyc
安装命令安全性
通过92
标准软件包或运行时安装路径
权限范围
失败22
secrets or environment access, shell or command execution
仓库证据
通过86
https://github.com/amd/skills/tree/main/skills/serving-llms-on-epyc
审查状态
信息66
可用 AI 审查数据
Agent 验证结果
信息54
暂未有 Agent 结果数据
检查项
安装与采用审查
安装路径
92
npx skills add amd/skills --skill serving-llms-on-epyc
仓库
88
https://github.com/amd/skills/tree/main/skills/serving-llms-on-epyc
许可证
86
MIT
维护
88
距上次推送 1 个月
AI 审查
55
The skill relies on external resources (Docker Hub image, Hugging Face model registry) which could introduce supply-chain risks if the image or registry is compromised; however, the skill pins a specific image and version, mitigating this.
README/SKILL.md 完整度
86
Usable description available
依赖风险
44
command execution surface, credential or environment access
安装命令安全性
92
标准软件包或运行时安装路径
权限范围
22
secrets or environment access, shell or command execution
Star/Fork 活跃度
57
332 个 Star，30 个 Fork; 当前元数据中没有议题活跃度信息
采用度
68
332 个 GitHub Stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
警告
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- The skill relies on external resources (Docker Hub image, Hugging Face model registry) which could introduce supply-chain risks if the image or registry is compromised; however, the skill pins a specific image and version, mitigating this.
- The skill assumes the agent has permission to run docker/podman commands without sudo; this is a stated prerequisite, but the skill does not verify user permissions beyond runtime detection.
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Stars/forks activity: 332 stars, 30 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
方法
本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。
对比相近选项