ClawHub
Back to skill

Security audit

Game

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only game design skill with a broad trigger, but it does not request tools, credentials, persistence, or system access.

Installers should be aware that this skill may activate for broad gamification or game-theory style requests, not only tabletop or video game design. It appears safe from a security perspective, but users who want narrower behavior should invoke it only for explicit game-design or gamification tasks.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description is extremely broad and can be triggered by many ordinary requests about games, education, habits, team productivity, or even real-life decision-making. Overly broad invocation language increases the chance the skill is selected when the user did not explicitly intend to use it, causing prompt hijacking of benign conversations and unnecessary exposure of the model to this skill's instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.