Security audit
Quality Review
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only review methodology skill with no code execution, credential use, persistence, or hidden behavior.
Installers should expect this skill to shape how an agent performs reviews and asks for evidence. It does not add executable behavior or privileged access, but users should still review any sources or commands an agent proposes during an actual review task.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.