Security audit
Agent Justice Protocol
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a disclosed local workflow for agent dispute investigation, with no evidence of hidden execution, exfiltration, or destructive behavior.
Before installing, verify the PyPI package and consider pinning a trusted version. Use only transaction-relevant evidence files, keep dispute stores private, and review fault or risk conclusions before using them for real decisions.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.