Agent Discovery
Security checks across malware telemetry and agentic risk
Overview
This is a simple instruction-only skill for finding and comparing public agent tools, with no code or hidden access requested.
This appears low risk to install as an advisory skill. Because it is brief and from a non-trusted publisher, review future versions for any newly added scripts, credential requests, network-download steps, or broader automation before upgrading.
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
66/66 vendors flagged this skill as clean.