Architecture
Security checks across malware telemetry and agentic risk
Overview
This architecture skill is advisory text only and does not request data access, code execution, persistence, credentials, or privileged actions.
This appears safe to install from an agentic-security perspective. Treat architecture, permitting, zoning, code, engineering, and liability guidance as general support and verify project-specific decisions with qualified local professionals.
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.