Vllm
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only vLLM deployment helper, with disclosed setup commands that fit its stated purpose.
Safe to install as a reference skill. Before running its commands, pin vLLM and Docker image versions, avoid mounting unnecessary local cache data, and secure any API server exposed on port 8000.
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.