Skill Trust Decision

multi-research

纯文档Skill,声明exec工具但无实际代码,声称安全功能但无法验证,仅依赖SKILL.md描述性内容驱动AI Agent。

Install decision first Source: ClawHub Scanned: Oct 10, 2026
Files 3
Artifacts 3
Violations 0
Findings 4

Why this conclusion was reached

0/4 dimensions flagged
Pass
Declared vs actual capability

Declared resources and inferred behavior are broadly aligned.

Review
Hidden execution and egress

3 lower-risk artifacts were extracted and still need context.

Pass
Attack chain and severe findings

There is no explicit malicious chain in the report.

Review
Dependencies and supply chain hygiene

4 dependency or supply-chain issues need attention.

What drove the risk score up

声明exec工具但无代码实现 +15

SKILL.md声明read和exec工具,但无scripts/代码文件,功能通过纯Markdown指令驱动Agent实现,存在权限声明过宽风险

安全声明无法验证 +10

声称使用AES加密、TLS/SSL、API密钥轮换等安全机制,但无代码实现

声称高级ML能力但无实现 +5

描述深度学习、贝叶斯网络等复杂技术,但仅提供文字说明,无任何模型代码或训练脚本

skill-card.md自认可疑 +5

发布者在skill-card.md中明确承认'security verdict is suspicious',请求宽泛命令访问和API密钥配置

Most important evidence

Medium Doc Mismatch

安全功能声称无代码支撑

SKILL.md包含完整的安全检查清单(API密钥加密存储、TLS传输、AES存储加密、日志脱敏),但该Skill为纯Markdown指令型,无任何代码文件实现这些安全机制。

SKILL.md:1
移除或明确标注安全功能声明仅作为设计意图,不代表实际实现
Medium Priv Escalation

exec工具声明超出功能需要

纯文档型Skill声明exec工具用于命令执行,但无脚本文件,实际通过自然语言指令驱动AI Agent执行操作,权限声明过宽。

SKILL.md:8
如无实际代码需要exec,应移除此工具声明或明确限定用途
Low Doc Mismatch

技术能力声称与实际不符

声称使用深度学习模型、贝叶斯网络、NLP情感分析等复杂技术,但仅提供数学公式和文字描述,无任何模型训练/推理代码。

SKILL.md:95
明确说明是否依赖外部API(如Tushare)还是声称本地ML能力
Low Supply Chain

依赖声明无版本锁定

环境要求声明pip install numpy pandas scikit-learn tensorflow,无版本锁定。

SKILL.md:182
添加版本锁定:numpy>=1.24.0 pandas>=2.0.0 scikit-learn>=1.3.0 tensorflow>=2.13.0

Declared capability vs actual capability

Filesystem Pass
Declared READ
→
Inferred READ
SKILL.md frontmatter tools: read
Shell Pass
Declared WRITE
→
Inferred WRITE
SKILL.md frontmatter tools: exec
Network Pass
Declared NONE
→
Inferred READ
声称集成Tushare Pro和AKShare API,无代码但AI Agent可能代为调用

Suspicious artifacts and egress

Medium External URL
https://skillhub.cn

SKILL.md:19

Medium External URL
https://clawhub.ai/user/thcjp

skill-card.md:9

Medium External URL
https://clawhub.ai/thcjp/skills/multi-research

skill-card.md:39

Dependencies and supply chain

PackageVersionSourceKnown vulnNotes
numpy * pip No 无版本锁定
pandas * pip No 无版本锁定
scikit-learn * pip No 无版本锁定
tensorflow * pip No 无版本锁定,依赖声明而非实际使用

File composition

3 files · 422 lines
Markdown 2 files · 417 linesJSON 1 files · 5 lines
Files of concern · 2
SKILL.md Markdown · 359 lines
安全功能声称无代码支撑 · exec工具声明超出功能需要 · 技术能力声称与实际不符 · 依赖声明无版本锁定 · https://skillhub.cn
skill-card.md Markdown · 58 lines
https://clawhub.ai/user/thcjp · https://clawhub.ai/thcjp/skills/multi-research
Other files · _meta.json

Security positives

无脚本代码,无法执行隐藏的恶意行为
skill-card.md发布者主动披露已知风险
投资建议部分包含人工审核提醒
错误处理框架较为完整