ClawHub
Back to skill

Security audit

Hugging Face Local Models

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed guidance for finding, downloading, converting, and running local Hugging Face GGUF models with llama.cpp.

Before installing, be aware that the skill may guide your agent to install or build llama.cpp, authenticate to Hugging Face for gated models, and download large model files. Use trusted model repositories, check model licenses, and keep any local llama-server bound appropriately for your environment.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · references/hardware.md (reported line 17)May include surrounding context.

md
llama-cli -m model.gguf -ngl 35 -p "Hello"

# Hybrid for large models
llama-cli -m llama-70b.Q4_K_M.gguf -ngl 20

# Multi-GPU split
llama-cli -m large-model.gguf --tensor-split 0.5,0.5 -ngl 60

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 82)May include surrounding context.

text

```bash
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer no-key" \
  -d '{