Security audit
ux-researcher
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only UX research helper with privacy considerations but no hidden code, install behavior, or privilege requests.
Safe to install as a UX research instruction skill. Before using it with real projects, avoid sharing raw participant records unless necessary, confirm consent and retention rules, de-identify data where possible, and require the agent to report only real study counts, participant counts, and measured outcomes.
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.
Static analysis
No suspicious patterns detected.