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.
boss-ai-assistant
Hardcoded DashScope API Key
LLM Proxy
Critical content-blocking disabled — credential exfiltration not prevented
samantha
Undeclared shell execution via subprocess ping sweep
monid
Remote script execution via curl|bash from mutable branch
moodle-connector
Hardcoded default password in MCP server bypasses security requirement
uplo-defense
Unpinned npm package execution via npx -y
crewai-team
Hardcoded API credential in 15 Python files
instreet-gomoku
Hardcoded API credential in source code
VLAN Linux Client Skill
Remote script piped to bash without integrity verification
openviking-context
Undeclared curl|bash remote script execution
interactive-infographic
Hardcoded fallback API key in source code
minimax-web-search
Hardcoded API Key in Source Code
minimax-cp
Hardcoded MiniMax API Key Exposed
risk-analysis
Hardcoded MySQL credentials in config.yaml
recruit-email-monitor
Hardcoded QQ Email Authorization Code
turing-pot-biglog
Undeclared base64 encoding of WebSocket messages