ClawHub
Back to skill

Security audit

gmod-addon-maker

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Garry's Mod addon helper with a slightly broad trigger description but no hidden execution, persistence, or sensitive access.

Installers should understand that this skill may be invoked for Lua-related prompts where Garry's Mod is only loosely relevant; otherwise, its behavior is disclosed and limited to helping build GMod addons.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description activates on broad terms such as 'Lua scripting' and 'GMod', which can cause the skill to trigger outside clearly intended addon-development requests. Over-broad activation increases the chance that this skill injects domain-specific instructions into unrelated conversations, leading to inappropriate tool use or instruction hijacking in contexts the user did not intend.

Static analysis

No suspicious patterns detected.