Agent
Security checks across malware telemetry and agentic risk
Overview
This is a minimal placeholder-like skill with no evident sensitive access or harmful behavior, though it does not implement the advertised network-agent functionality.
Install only if you are comfortable with a very small, likely placeholder skill. It does not show harmful behavior or sensitive access, but users expecting a working Billions Network task-management or node agent should verify functionality separately.
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.