Skill 审计报告
skvm-jit 审计报告.
Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any skill (not just SkVM-compiled ones) when the outcome was a failure, was partial, or the skill's instructions clearly caused confusion or an unnecessary detour. Clean successful runs usually do not need an optimization pass. For general skvm usage (profile/aot-compile/bench/proposals), use the sibling `skvm-general` skill instead.
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76
552 个 GitHub Stars
Star/Fork 活跃度
信息71
552 个 Star，54 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 2 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46
command execution surface, credential or environment access
安装可用性
通过92
npx skills add SJTU-IPADS/SkVM --skill skvm-jit
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18
secrets or environment access, shell or command execution
仓库证据
通过86
https://github.com/SJTU-IPADS/SkVM/tree/main/skills/skvm-jit
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 SJTU-IPADS/SkVM --skill skvm-jit
仓库
88
https://github.com/SJTU-IPADS/SkVM/tree/main/skills/skvm-jit
许可证
86
MIT
维护
88
距上次推送 2 个月
AI 审查
55
SKILL.md assumes the `skvm` CLI is already installed and does not describe how to verify availability or handle a missing/unavailable command.
README/SKILL.md 完整度
86
Usable description available
依赖风险
46
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
18
secrets or environment access, shell or command execution
Star/Fork 活跃度
71
552 个 Star，54 个 Fork; 当前元数据中没有议题活跃度信息
采用度
88
552 个 GitHub Stars
警告
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- SKILL.md assumes the `skvm` CLI is already installed and does not describe how to verify availability or handle a missing/unavailable command.
- The command example passes `--skill=<dir>` without quoting; paths containing spaces or shell metacharacters could be mishandled.
- The optimizer model identifier `openrou` is not explained; users may not know whether it is a required configured model or a typo.
- The included adapter-skill-paths.md excerpt appears truncated, though the documented path resolution approach is otherwise sound.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- 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