ClawHub
Back to skill

Security audit

test

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Godot gameplay scripting skill with no installer, executable code, credential handling, or hidden runtime behavior.

Installers should understand this skill may steer Godot-related work toward strict typing, signals, component composition, and advanced Godot techniques. Review generated code as usual, especially for C++ extensions or custom networking, but the package itself shows no hidden or disproportionate behavior.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The manifest describes an expert 'godot gameplay scripter', which reasonably covers gameplay systems in GDScript/C#, scene architecture, and signals. However, the advanced capabilities section adds GDExtension/C++ development, direct RenderingServer usage, and custom networking stacks/WebRTC, which are separate low-level engine, native plugin, and networking specialties not justified by the stated gameplay-scripting purpose.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The phrase 'Reference this agent by name or specialty when you need its expertise' does not define specific trigger phrases or clear activation boundaries. Terms like 'specialty' and 'need its expertise' are broad enough to overlap with ordinary discussion of Godot gameplay work, increasing the risk of unintended invocation.

Static analysis

No suspicious patterns detected.