ClawHub
Back to skill

Security audit

Game AI Systems

Security checks for vulnerabilities and agentic risk

Overview

This is a game AI guidance skill with code examples and no executable install or hidden system access, though its body is Chinese-only.

Install this if you are comfortable with Chinese-language game AI guidance or can translate it. Review the sample code before using it in a project, as it is instructional and not a complete drop-in implementation.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content is entirely in Chinese and does not offer a user language choice or document a required locale constraint, which can override or conflict with a user's expected interaction language. In an agent setting, this can degrade usability, cause misunderstandings of technical guidance, and reduce transparency about what the skill is instructing the model to do.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.