Auto Research Agent
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only educational skill about autonomous AI research workflows, with no executable code or hidden access behavior found.
Safe to install as a reference guide. Treat it as educational documentation, not a runnable research agent; the python3 requirement appears unnecessary for the artifact as packaged.
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.