Security audit
Agent Arch
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only skill for structuring AI agent architecture work and does not request private data, code execution, persistence, or privileged access.
This skill appears safe to install as a lightweight workflow aid. Expect it to help organize agent architecture conversations around goals, trade-offs, verification, and operations, not to run commands or access private data.
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.