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
risk-analysis
Hardcoded MySQL credentials in config.yaml
Manual upload Apr 4, 2026
Open Report ↗
Review
rundev-local-dev
Dangerous curl|bash Installation Pattern
Manual upload Apr 4, 2026
Open Report ↗
Review
colmena-manager
Command injection via agentId in multiple exec() calls
Manual upload Apr 4, 2026
Open Report ↗
Review
semanticfs
Dangerous curl|bash remote script execution
Manual upload Apr 4, 2026
Open Report ↗
Review
token-sop
Misleading privacy claim
Manual upload Apr 4, 2026
Open Report ↗
Review
clawschool
Undeclared shell execution requirement
Manual upload Apr 4, 2026
Open Report ↗
Review
file-transfer-thru-local-workspace
Undeclared credential file access
Manual upload Apr 4, 2026
Open Report ↗
Review
cms-meeting-monitor
Undeclared cross-skill subprocess execution
Manual upload Apr 4, 2026
Open Report ↗
Review
China Stock Sentiment
Undeclared shell execution via child_process.execSync
Manual upload Apr 4, 2026
Open Report ↗
Review
promptbuddy
Missing Implementation Files
Manual upload Apr 4, 2026
Open Report ↗
Review
swarmrecall
Comprehensive agent context exfiltration to third-party
Manual upload Apr 4, 2026
Open Report ↗
Review
openclaw-usage-manager
API tokens stored in plaintext on disk
Manual upload Apr 4, 2026
Open Report ↗
Review
search
Hardcoded API Credential in Source Code
Manual upload Apr 4, 2026
Open Report ↗
Review
lock-me-in
Undeclared stealth/anti-detection browser scripts
Manual upload Apr 4, 2026
Open Report ↗
Review
calendar_memo
Undeclared shell command execution
Manual upload Apr 4, 2026
Open Report ↗
Review
MemOptimizer (记忆优化器)
Undeclared shell execution via child_process.exec()
Manual upload Apr 4, 2026
Open Report ↗