中文 EN
Start Review
Skill Trust Decision

alibabacloud-workbench-cli

该技能为纯文档型工具封装，使用 curl|bash 远程脚本安装存在供应链风险，且无法验证外部安装源完整性

Install decision first Source: ClawHub Scanned: 16 hr ago
Files 3
Artifacts 5
Violations 0
Findings 3
Most direct threat evidence
01
用户安装技能后执行安装命令 Entry · SKILL.md
02
curl|bash 执行可能被篡改的远程脚本 Escalation · SKILL.md
03
安装来源服务器被入侵时可能植入恶意代码 Impact · https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh

Why this conclusion was reached

2/4 dimensions flagged
Pass
Declared vs actual capability

Declared resources and inferred behavior are broadly aligned.

Block
Hidden execution and egress

1 high-risk artifacts or egress signals were extracted.

Block
Attack chain and severe findings

The report includes 3 attack-chain steps and 1 severe findings.

Review
Dependencies and supply chain hygiene

Dependency information is incomplete, so supply-chain confidence stays limited.

Attack Chain

01
用户安装技能后执行安装命令

Entry · SKILL.md:29

02
curl|bash 执行可能被篡改的远程脚本

Escalation · SKILL.md:29

03
安装来源服务器被入侵时可能植入恶意代码

Impact · https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh:1

What drove the risk score up

curl|bash 远程脚本执行 +20

SKILL.md:29 声明通过管道执行远程安装脚本，虽然有风险警告但未提供完整性验证方法

无实际代码审查 +15

纯文档型技能，无法验证 workbench CLI 二进制实际行为

文档-行为一致性 +10

无脚本文件可供交叉验证，仅依赖外部工具

Most important evidence

High Supply Chain

curl|bash 远程脚本执行

技能文档中明确指导用户通过管道执行远程安装脚本 (https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh)，虽然 skill-card.md 在 Known Risks 中提及此风险，但未提供 SHA256 校验或其他完整性验证手段

SKILL.md:29
添加 GPG 签名校验或 SHA256 哈希验证步骤
Medium Credential Theft

敏感凭证本地存储

技能配置存储 AccessKey ID/Secret 到 ~/.workbench/config.json，文档仅建议 chmod 600 但未强制检查

SKILL.md:45
优先使用 RamRoleArn 或 CredentialsURI 模式避免长期密钥存储
Low Doc Mismatch

外部工具行为不可验证

技能为纯文档封装，实际能力取决于 workbench CLI 二进制，无法通过代码审查验证其真实行为

SKILL.md:1
建议 skill 作者提供 workbench CLI 源码审计报告或官方签名

Declared capability vs actual capability

Shell Pass
Declared WRITE
→
Inferred WRITE
SKILL.md:29 声明 Bash 执行安装命令
Filesystem Pass
Declared WRITE
→
Inferred WRITE
SKILL.md:45 写入 ~/.workbench/config.json
Network Pass
Declared READ
→
Inferred READ
连接 *.aliyuncs.com 和 Workbench WebSocket 端点

Suspicious artifacts and egress

Critical Dangerous Command
curl -fsSL https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh | bash

SKILL.md:29

Medium External URL
https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh

SKILL.md:29

Medium External URL
https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.ps1

SKILL.md:35

Medium External URL
https://clawhub.ai/user/sdk-team

skill-card.md:7

Medium External URL
https://clawhub.ai/sdk-team/skills/alibabacloud-workbench-cli

skill-card.md:34

Dependencies and supply chain

There are no structured dependency warnings.

File composition

3 files · 428 lines
Markdown 3 files · 428 lines
Files of concern · 2
SKILL.md Markdown · 349 lines
curl|bash 远程脚本执行 · 敏感凭证本地存储 · 外部工具行为不可验证 · curl -fsSL https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh | bash · https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.sh · https://workbench-cli.oss-cn-hangzhou.aliyuncs.com/install.ps1
skill-card.md Markdown · 47 lines
https://clawhub.ai/user/sdk-team · https://clawhub.ai/sdk-team/skills/alibabacloud-workbench-cli
Other files · ram-policies.md

Security positives

skill-card.md 明确列出了 Known Risks 和 Mitigations
包含完整的 RAM 权限声明 (references/ram-policies.md)
提供了实例级别的权限限制建议
内置覆盖保护和破坏性命令确认机制
支持多种认证模式包括零信任集成