Ai Agents Architect
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only skill for designing AI agents, with no evidence of hidden behavior, install-time execution, credential access, or unsafe persistence.
Reasonable to install if you want AI-agent architecture guidance. Review any code it helps generate before running it, especially if adapting the memory, tool-use, or multi-agent examples to real credentials, files, or external services.
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
66/66 vendors flagged this skill as clean.