Security audit
Runbook Example Catalog
Security checks across malware telemetry and agentic risk
Overview
This skill is a small, non-executable runbook example that records a command option and does not request sensitive access.
This appears safe to install for controlled runbook-option cataloging. It is still a very narrow validation-style skill, so users should only expect it to return the documented option record rather than perform real operational work.
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
64/64 vendors flagged this skill as clean.