Skill Trust Decision
llm-assistant-hub
纯Markdown指令技能包，声明exec工具但无代码实现，文档-行为差异风险低但权限声明宽泛
Why this conclusion was reached
0/4 dimensions flagged Pass
Declared vs actual capability
Declared resources and inferred behavior are broadly aligned.
Pass
Hidden execution and egress
No obvious high-risk egress or execution signals were found.
Pass
Attack chain and severe findings
There is no explicit malicious chain in the report.
Review
Dependencies and supply chain hygiene
Dependency information is incomplete, so supply-chain confidence stays limited.
What drove the risk score up
权限声明宽泛 +20
声明exec工具但无代码实现，文档中未明确说明为何文档分析需要命令行执行能力
无可验证代码 +15
仅有SKILL.md，无法验证声明的tools与实际行为是否一致
Most important evidence
Medium Priv Escalation
声明exec但无代码验证
tools字段声明exec（shell:WRITE级别命令执行），但该技能包仅含SKILL.md无scripts/代码。无法验证exec的实际用途和范围
SKILL.md:1 提供代码实现以验证exec用途，或将exec从tools声明中移除
Low Doc Mismatch
安全告示内容模糊
安全告示提到'命令执行受白名单约束'但未说明白名单内容或exec的实际使用场景
SKILL.md:245 明确说明exec工具在文档分析场景中的具体用途
Low Doc Mismatch
上线流程描述混乱
上线流程章节包含多个编号混乱的步骤，提及API密钥配置、文件处理、命令执行等多个场景，与主要功能（文档分析）关联不清晰
SKILL.md:280 整理上线流程，统一描述文档分析场景的实际操作步骤
Declared capability vs actual capability
Filesystem Pass
Declared READ|WRITE
→ Inferred READ
tools字段声明read/write，符合文档分析场景 Shell Pass
Declared WRITE
→ Inferred UNKNOWN
tools字段声明exec但无代码文件验证 Network Pass
Declared NONE
→ Inferred NONE
文档未声明网络访问能力 Skill Invoke Pass
Declared NONE
→ Inferred NONE
无跨技能调用 Suspicious artifacts and egress
No obvious IOC was extracted.
Dependencies and supply chain
There are no structured dependency warnings.
File composition
1 files · 382 lines
Markdown 1 files · 382 lines
Files of concern · 1
SKILL.md 声明exec但无代码验证 · 安全告示内容模糊 · 上线流程描述混乱
Security positives
纯Markdown指令包，无代码执行路径
声明的网络访问能力为NONE，符合文档分析场景
安全告示包含API密钥管理、数据暴露等基本安全提示
无外部依赖声明，无供应链风险