ClawHub
Back to skill

Security audit

optiq-local-models

Security checks for vulnerabilities and agentic risk

Overview

This skill provides proportionate instructions for running a local language model, with user approval required before downloads or server startup.

Install mlx-optiq separately from its documented source, allow for several gigabytes of model storage, and keep the server on 127.0.0.1 unless you deliberately configure authenticated network access. Stop the server when finished.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The server speaks the OpenAI chat API at http://127.0.0.1:8080/v1. optiq serve --help lists the other endpoints it exposes. Smoke test:

bash
curl http://127.0.0.1:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"mlx-community/Qwen3.5-9B-OptiQ-4bit","messages":[{"role":"user","content":"Say hello in five words."}],"max_tokens":32}'

Static analysis

No suspicious patterns detected.