Skill Trust Decision

image-knowledge-converter

文档声明了文件系统写入、shell执行、外部API调用等敏感能力,但实际打包中无任何代码文件,文档-行为完全脱节,存在文档诱饵或虚假技能包风险

Install decision first Source: ClawHub Scanned: 23 days ago
Files 1
Artifacts 0
Violations 0
Findings 3

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

文档-行为完全脱节 +25

文档描述了多个Python脚本的执行流程,但实际打包中无任何代码文件

声明敏感能力无代码验证 +15

文档描述了subprocess、API调用、配置写入等操作,但无法验证是否真的执行这些操作

声称安全实践但无代码支撑 +10

声称'API密钥不通过对话传递'的安全原则,但无代码验证此说法

Most important evidence

Medium Doc Mismatch

文档声明功能但无实际代码

SKILL.md详细描述了auto_process_all_v9_4.py、wizard_processor.py等脚本的执行流程,但打包中无任何.py文件

SKILL.md:1
验证技能包完整性,要求提供实际脚本代码
Medium Doc Mismatch

声称安全实践无法验证

文档声称'API密钥不通过对话传递,用户直接在本地模板文件中填写',但无代码验证此安全声明

SKILL.md:35
需要代码审查验证密钥处理流程
Low Supply Chain

声明依赖但无依赖文件

文档提及requests库等依赖,但无requirements.txt或package.json

SKILL.md:1
提供明确的依赖管理文件

Declared capability vs actual capability

Filesystem Pass
Declared WRITE
Inferred UNKNOWN
文档声明创建配置文件,但无代码验证
Network Pass
Declared WRITE
Inferred UNKNOWN
文档声明调用腾讯云、百度云API,但无代码验证
Shell Pass
Declared WRITE
Inferred UNKNOWN
文档声明执行python脚本,但无代码验证

Suspicious artifacts and egress

No obvious IOC was extracted.

Dependencies and supply chain

There are no structured dependency warnings.

File composition

1 files · 229 lines
Markdown 1 files · 229 lines
Files of concern · 1
SKILL.md Markdown · 229 lines
文档声明功能但无实际代码 · 声称安全实践无法验证 · 声明依赖但无依赖文件

Security positives

文档结构完整,版本历史清晰
声称采用安全密钥管理实践(本地模板文件)
支持多种云服务(腾讯云、百度云)
无敏感文件泄露风险(无实际代码)