Security audit
Safe Exec Wrapper
Security checks across malware telemetry and agentic risk
Overview
This skill is a small defensive wrapper that labels command output as untrusted; it does not sandbox the command itself.
Install this if you want a helper that makes untrusted command output easier for an agent to treat as data. Continue reviewing the underlying command first, especially commands that modify files, contact services, or use credentials, because safe-exec does not sandbox execution or prevent side effects.
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.