AI-First Engineering
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only engineering guidance skill with no executable install steps or credential access.
This appears safe to install as an opinionated documentation skill. Treat its testing and review recommendations as team-process guidance, and adapt them to your project’s risk level rather than as mandatory automated 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
67/67 vendors flagged this skill as clean.