User Research
Security checks across malware telemetry and agentic risk
Overview
This is a plain user-research guidance skill with no scripts, persistence, credential use, or hidden data handling.
This skill appears safe to install for user-research planning. As with any research workflow, avoid sharing unnecessary customer personal data, confidential business metrics, or sensitive interview notes unless you intend the agent to process them.
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
63/63 vendors flagged this skill as clean.