ClawHub
Back to skill

Security audit

Mac Mini AI — Mac Mini Local LLM, Image Gen, STT on Apple Silicon

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local Mac Mini AI setup guide, with a normal supply-chain caveat around an unpinned PyPI install.

Install in a virtual environment and consider pinning `ollama-herd` to a reviewed version. Expect the tool to run a local/LAN AI service, process prompts and uploaded files locally, and write disclosed fleet-manager logs/configuration.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:43
Finding

Unpinned Third-Party Package Installation

Content
View full analysis
Remediation
View remediation
" ``` 2. Publish cryptographic hashes for approved distributions and install through a requirements file using: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 3. Recommend installation inside a dedicated virtual environment or another isolated execution environment rather than the user's global Python environment. 4. Link to a specific source revision or release tag so users can verify that the installed artifact corresponds to reviewed source code. 5. Document the expected package publisher, signature or provenance information, and supported version. 6. Periodically review pinned versions for known vulnerabilities before updating the recommended release. ]]>

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

bash
# Fleet overview
curl -s http://localhost:11435/fleet/status | python3 -m json.tool

# Model recommendations for your hardware
curl -s http://localhost:11435/dashboard/api/recommendations | python3 -m json.tool

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

curl -s http://localhost:11435/fleet/status | python3 -m json.tool

Model recommendations for your hardware

curl -s http://localhost:11435/dashboard/api/recommendations | python3 -m json.tool

text

## Works with any OpenAI-compatible tool

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 77)May include surrounding context.

Ollama API

bash
curl http://localhost:11435/api/chat -d '{
  "model": "gemma3:12b",
  "messages": [{"role": "user", "content": "Explain recursion simply"}],
  "stream": false