Agent Discovery
Security checks across malware telemetry and agentic risk
Overview
This is a small instruction-only skill for discovering and comparing public agents, with no code, install actions, credential use, or persistence.
This skill appears safe to install as a lightweight research helper. Verify any agent recommendations, integration advice, and cost estimates independently before acting on them, especially if business systems or paid services are involved.
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.