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.
face-analysis
Hardcoded Database Credentials in config.yaml
heycube-setup
Undeclared persistent hook installation
boss-ai-assistant
Hardcoded DashScope API Key
LLM Proxy
Critical content-blocking disabled — credential exfiltration not prevented
monid
Remote script execution via curl|bash from mutable branch
backup-2-github
Hardcoded Default Repository Exposes User Data
uplo-defense
Unpinned npm package execution via npx -y
VLAN Linux Client Skill
Remote script piped to bash without integrity verification
openviking-context
Undeclared curl|bash remote script execution
minimax-web-search
Hardcoded API Key in Source Code
shekel-hyperliquid
Mandatory dynamic instruction fetching — silent remote code replacement
token-sop
Automatic workflow contribution enabled by default
mind-wander
Undeclared arbitrary Python code execution via sandbox_run()
moltspay_skill
Untrusted third-party npm package installed without pinning
openclaw-memory-auto
Hardcoded Windows username path leaks user identity
product-demo-video
Destructive `rm -rf` glob command in install script