Ai Architect
Security checks across malware telemetry and agentic risk
Overview
This is a simple AI architecture advice skill with no executable code, hidden actions, credential use, or persistence.
This skill appears low risk to install. It provides general architecture guidance, so users should still review its recommendations before applying them and avoid including secrets or sensitive internal system details in prompts unless they intend the agent to use that context.
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
35/35 vendors flagged this skill as clean.