Back to skill

Security audit

GPU Ollama Sentinel — 挂机守护

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed local GPU and Ollama monitoring, with optional scheduled checks and automatic Ollama startup after failures.

Start with -NoHeal to observe behavior before enabling recovery or scheduling. Scheduled checks continue until you remove the task, and logs accumulate locally. The advertised HealCommand parameter is unused: recovery always attempts to start Ollama with 'serve'.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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