Autonomous Execution
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only autonomy skill that tells the agent to finish in-scope work while stopping for sensitive actions.
Before installing, understand that this skill is meant to make the agent proceed through non-sensitive subtasks without repeated prompts. Use it with a clearly scoped workspace and task, and expect the agent to ask before sensitive actions such as sending messages, deleting data, using secrets, changing system settings, or running elevated commands.
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.