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.
claw-office-report
Undisclosed data exfiltration — full task text sent to external server
skill-security-vet
Undeclared local/full computer scanning mode
skill-gatekeeper
Undeclared child_process.exec with hardcoded path
ClawSafe AI Skills Portfolio
Hardcoded API key in ClawHub monitoring tool
openclaw-cursor-agent
Dangerous curl|bash pattern in documentation
memex
Hidden Telemetry with Evasion-Intent Comment
superguard
Hidden garbled text in metadata likely containing prompt injection
agent-p2p
Hardcoded default password for admin backend
async-command
Hardcoded External IP Address
token-watchdog
Undeclared Shell Execution via execSync
whale-alert-monitor
Hardcoded billing API key in payment.py
clawhub-security-scan
Hardcoded high-entropy string contradicts security advice
claw-body
Undeclared shell execution via execSync
ai-redaction
Obfuscated compiled JavaScript hides functionality
odds-movement-monitor
Hardcoded Billing API Key
swarm-control-feishu
Dangerous curl|bash pattern in documentation