MIT Reasoning Lite
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-only reasoning aid with a simple local installer and no evidence of hidden data access, networking, or unsafe behavior.
This appears safe to install as a reasoning prompt. Manual use by copying SKILL.md is straightforward; running install.sh may fail because the package does not include every file the script tries to copy.
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
65/65 vendors flagged this skill as clean.