Skill 审计报告
foundation-models 审计报告.
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
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
700 个 GitHub Stars
Star/Fork 活跃度
信息71
700 个 Star，67 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 3 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 rshankras/claude-code-apple-skills --skill foundation-models
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24
secrets or environment access, shell or command execution
仓库证据
通过86
https://github.com/rshankras/claude-code-apple-skills/tree/main/skills/apple-intelligence/foundation-models
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 rshankras/claude-code-apple-skills --skill foundation-models
仓库
88
https://github.com/rshankras/claude-code-apple-skills/tree/main/skills/apple-intelligence/foundation-models
许可证
86
MIT
维护
88
距上次推送 3 个月
AI 审查
55
No explicit prompt-injection defense guidance appears in SKILL.md; companion safety docs cover guardrails, but a dedicated note about untrusted input handling would strengthen the skill.
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
24
secrets or environment access, shell or command execution
Star/Fork 活跃度
71
700 个 Star，67 个 Fork; 当前元数据中没有议题活跃度信息
采用度
88
700 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
- No explicit prompt-injection defense guidance appears in SKILL.md; companion safety docs cover guardrails, but a dedicated note about untrusted input handling would strengthen the skill.
- Bash is listed as an allowed tool even though the documented workflow is primarily code reference and editing; unnecessary shell access broadens the agent's permission surface.
- 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
- 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