最近有哪些 skills
不值得默认信任
这不是热度榜。这里展示的是最近被送来判断、且系统认为需要阻止或至少人工复核的 skills。重点不是它们多流行,而是为什么它们不该被直接装进环境。
exploration-mode-skill
Undeclared autonomous execution
jef1test
All API data routed through third-party proxy
gougoubi-activate-and-stake-risklp
Referenced scripts not included in package
PV_12
Vague capability claims without verification
interactive-infographic
Hardcoded fallback API key in source code
risk-analysis
Hardcoded MySQL credentials in config.yaml
isnad-security-kit
installer.js performs zero actual installation
rundev-local-dev
Dangerous curl|bash Installation Pattern
cogdx-health
Missing allowed-tools declaration
ai-customer-service-automation
Declared functionality has no implementation
ai-enterprise-knowledge-base
Remote code execution via git clone
ai-intelligent-helpdesk
No implementation code present
turing-pot-biglog
Undeclared base64 encoding of WebSocket messages
colmena-manager
Command injection via agentId in multiple exec() calls
x-scout
Silent phone-home analytics on every execution
ecommerce-category-collector
Hardcoded credentials in documentation