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.
cogdx-health
Missing allowed-tools declaration
ai-enterprise-knowledge-base
Remote code execution via git clone
turing-pot-biglog
Undeclared base64 encoding of WebSocket messages
shekel-hyperliquid
Mandatory dynamic instruction fetching — silent remote code replacement
x-scout
Silent phone-home analytics on every execution
semanticfs
Dangerous curl|bash remote script execution
token-sop
Automatic workflow contribution enabled by default
ai-content-pipeline
Production API credentials in .env file
mind-wander
Undeclared arbitrary Python code execution via sandbox_run()
moltspay_skill
Untrusted third-party npm package installed without pinning
ai-beauty
Contradictory claim of local-only processing
openclaw-memory-auto
Hardcoded Windows username path leaks user identity
cms-meeting-monitor
Undeclared cross-skill subprocess execution
likes-training-planner
Dangerous curl|bash installation pattern
product-demo-video
Destructive `rm -rf` glob command in install script
kuaidi-query
Hardcoded API Credentials Exposed