Ai Agents Architect
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only AI agent architecture guide with no hidden install behavior or credential access found.
This skill appears reasonable to install as a design assistant. Before running any agent code generated with its help, review tool permissions, memory persistence, logging, external API calls, and approval flows.
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.