Security audit
Agent Governance Assistant
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only governance skill that helps users structure AI agent audits and compliance reports, with no executable behavior or hidden data access.
Before installing, users should understand that effective use may require sharing sensitive enterprise governance details such as agent inventories, data access levels, endpoints, and compliance gaps. Verify regulatory claims against official sources before relying on generated reports for legal or regulatory filings.
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.