Security audit
LLM Inference Radar
Security checks across malware telemetry and agentic risk
Overview
This is a research-workflow skill for LLM inference intelligence briefs, with disclosed web research and optional local knowledge-base updates that fit its stated purpose.
Reasonable to install if you want a structured LLM inference research radar. Expect it to browse current public sources and, when asked or when durable feedback is given, maintain local research notes; review that behavior if you do not want persistent preference or knowledge-base files.
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.