Security audit
Mingjing— AI Agent Health Center
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a disclosed local agent health-monitoring setup, with expected caveats around installing external packages and running a local daemon/dashboard.
Before installing, verify the external `mingjing` package and `mingjing-probe` plugin provenance, review what telemetry is stored locally, and confirm how to stop the daemon and local web dashboard when not in use.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.