Security audit
UserTold Recruit Participants
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent recruitment-planning guide for UserTold studies and does not show hidden execution, credential use, or unsafe automation.
Before installing, understand that this skill can help prepare and, with your explicit approval, update UserTold study configuration. Review generated recruitment copy, reward terms, visibility rules, and intake questions carefully, and keep personal identifiers out of URLs and source tags.
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.