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.
lock-me-in
Undeclared stealth/anti-detection browser scripts
task-progress-stream
Undeclared shell command execution
calendar_memo
Undeclared shell command execution
openclaw-security-patrol
Extensive device fingerprinting under --push mode
MemOptimizer (记忆优化器)
Undeclared shell execution via child_process.exec()
claw-shell
Unrestricted shell execution with weak safety controls
aagent-system
Undeclared External Script Execution
feishu-evolver-wrapper
Dynamic code evaluation on untrusted input
self-evolution-engine
Hardcoded Billing API Key in Source Code
buy-domain-helper
Undeclared shell execution via execSync and spawn
security-defense-line
Hardcoded API Key in Source Code
melo-tts-metadata-creator
Undeclared silent package installation
chattts
Hardcoded fallback IP address
long-term-memory
Hardcoded API Key in Source Code
飞书机器人配置助手
文档中记录curl|bash远程脚本执行命令
wip-xai-grok
Undeclared shell:WRITE via 1Password CLI execSync