Ai Agents Architect
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only AI agent architecture guide with no executable install behavior or hidden access requests.
This skill appears reasonable to install as guidance material. Review any agent code you later generate from its examples before running it, especially if you add real tools, credentials, persistent memory, network access, or autonomous actions.
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.