Async Command
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only guide for running and stopping long shell commands asynchronously, with no hidden install behavior or data access.
Install this if you want agents to manage long-running commands without blocking. The main risk is the normal risk of shell execution: keep commands task-scoped, require care for destructive or privileged operations, and make sure background jobs are polled or stopped when no longer needed.
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
VirusTotal findings are pending for this skill version.