Skill AGI
Security checks across malware telemetry and agentic risk
Overview
This is a simple memory-note skill with disclosed persistence behavior, but users should review notes before promoting them into long-term agent memory.
Install this if you want a lightweight persistent lesson log. Do not record secrets or untrusted instructions, and only promote entries into long-term agent memory after confirming they are accurate, still useful, and safe to apply in future sessions.
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
63/63 vendors flagged this skill as clean.