Security audit
nonblocking-agent-execution
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent guide for running long agent tasks without blocking, with its background-process behavior clearly disclosed.
Install only if you want agents to manage long-running commands with detached background jobs. Review any command before starting it, monitor ~/.jobs logs/status, and stop or clean up jobs you no longer need.
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.
Static analysis
No suspicious patterns detected.