Security audit
Agent Dna
Security checks across malware telemetry and agentic risk
Overview
This skill is a small Markdown-only guide for evaluating agent behavior and does not include executable code or hidden install behavior.
Before installing, understand that the skill is meant to reason about agent identity, permissions, behavior history, and approvals. That kind of monitoring can involve sensitive operational context, so use it where tracking and audit trails are appropriate, but this package itself does not contain code that performs collection or enforcement.
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.