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.
sensitive-profile-audit
Undeclared SHA256 fingerprinting of credential directories
risk-analysis
Hardcoded MySQL credentials in config.yaml
cogdx-health
Missing allowed-tools declaration
x-scout
Silent phone-home analytics on every execution
token-sop
Automatic workflow contribution enabled by default
maxianer
Undeclared external data transmission
ai-beauty
Contradictory claim of local-only processing
gateway-monitor-installer
Undeclared external network access
lessac_offline_voice_system
False claim of offline operation
swarmrecall
Comprehensive agent context exfiltration to third-party
search
Hardcoded API Credential in Source Code
微信助手智能网关 (wechat-ai-bridge)
Undeclared external network communication
openclaw-security-patrol
Extensive device fingerprinting under --push mode
self-evolution-engine
Hardcoded Billing API Key in Source Code
rewrite_question
Network capability declared as NONE but actual traffic exists
awareness-memory
Undeclared session file exfiltration to external cloud