Shell Safe Exec
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only safety skill for repo-local build and test commands, with no executable payload, credential use, persistence, or hidden behavior found.
This skill is reasonable to install if you want an agent to run safe project-local checks. Review dependency install commands before approving them, since package managers can execute third-party scripts, and use it only in workspaces you trust.
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.