Worker Safety
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only safety skill that tells agents to refuse risky operations and does not install code or request sensitive access.
Install this if you want agents to enforce rigid safety boundaries. Expect it to refuse some administrative or cleanup requests, including bulk installs, runtime upgrades, unsafe network exposure, and deletion of protected workspace files.
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.