AI Researcher
Security checks across malware telemetry and agentic risk
Overview
This appears to be a disclosed research-assistant skill, with no artifact-backed evidence of hidden execution, credential use, persistence, or data theft.
Review the external context-pack link as a separate website before spending money or sharing information there. The skill itself appears proportionate for research assistance and does not show evidence of hidden authority or unsafe behavior.
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.