AI Agent Manager Playbook
Security checks across malware telemetry and agentic risk
Overview
This is an instructional AI-agent management playbook with no code execution, credential use, persistence, or hidden data movement in the reviewed artifacts.
This skill appears safe to install as a playbook. Treat its generated recommendations as operational advice: review before changing agent permissions, retiring agents, changing governance policies, or using the linked paid external resources.
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.