Agent Ops Runbook
Security checks across malware telemetry and agentic risk
Overview
This skill is a markdown-only planning aid for creating AI agent deployment runbooks and does not ask the agent to run commands, access data, or persist anything.
Safe to install as a runbook drafting aid. Treat its generated output as planning guidance, and have engineering, security, and compliance reviewers validate any production deployment, rollback, monitoring, cost, or regulated-data decisions before acting on them.
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.