research-sources
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only research-source selection skill with no executable code, credentials, persistence, or hidden system access.
This appears safe to install as a low-risk guidance skill. Users should still review any suggested external sources before relying on them, and any actual browsing or monitoring will use the permissions of their normal agent tools.
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.