Which skills recently failed
or triggered trust review
This is not a popularity board. It shows recently reviewed skills that the system believes should be blocked or at least manually reviewed. The point is not how popular they are, but why they should not be installed blindly.
Review
multi-research
文档包含可疑表述
ClawHub 28 days ago
Open Report ↗
Review
taskfuel
远程脚本管道执行
ClawHub 28 days ago
Open Report ↗
Review
smyx-child-focus-analysis-analysis
隐式凭证管理机制
ClawHub Aug 11, 2026
Open Report ↗
Review
coppa-check
--non-interactive 模式影子联网行为
ClawHub Aug 10, 2026
Open Report ↗
Review
precc
危险的远程脚本执行安装方式
ClawHub Aug 8, 2026
Open Report ↗
Review
cloud-ops-orchestrator
文档占位符泛滥
ClawHub Aug 8, 2026
Open Report ↗
Review
sa-master
Hardcoded bearer token in config.json
ClawHub Aug 1, 2026
Open Report ↗
High Risk
yqzl-ai-service
Automatic code download and execution without consent
ClawHub Jul 28, 2026
Open Report ↗
Review
url-manager
文档包含危险 Shell 命令
ClawHub Jul 23, 2026
Open Report ↗
Review
dlazy-idea2video
文档-行为严重不符
ClawHub Jul 21, 2026
Open Report ↗
Review
moltspay-skill
Undeclared external npm dependency
ClawHub Jul 8, 2026
Open Report ↗
Review
x402-compute
远程脚本管道执行
ClawHub Jul 6, 2026
Open Report ↗
High Risk
psychology-analysis
静默phoneLogin调用
ClawHub Jun 28, 2026
Open Report ↗
Review
wechat_bridge
Hardcoded credentials in wechat.yaml
ClawHub Jun 24, 2026
Open Report ↗
Review
子网计算服务
Skill repurposed from unrelated gaokao/school service
ClawHub Jun 24, 2026
Open Report ↗
High Risk
auto-skill-hunter
Undeclared shell:WRITE via execSync — git clone
ClawHub Jun 24, 2026
Open Report ↗