Security audit
Local Inference Context
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill gives local LLM context-management guidance and does not show hidden, destructive, or unrelated behavior.
Install if you want help managing context pressure on local LLM backends. Expect the agent to suggest local diagnostic commands and memory checkpoints; review commands before running them and keep checkpoints free of credentials, tokens, and sensitive log contents.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.