ClawHub
Back to skill

Security audit

Local Model Quantization Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small local recommendation helper, and its optional file input and output behavior is disclosed and user-directed.

Before installing, use explicit paths for --hardware and --output and avoid pointing --output at important files. The skill appears suitable for local routing advice and does not download models or change configuration.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes a local script with an optional output path and references optional hardware JSON input, which implies file read/write behavior, but it does not declare any tool scope or permissions boundaries in the skill manifest. This creates an avoidable trust gap: an agent or operator may run a skill that can access local files without explicit disclosure or restriction, increasing the chance of unintended file access or writes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.