Back to skill

Security audit

OpenGame Browser Game Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed browser-game prototyping skill with no hidden executable code, persistence, or credential handling.

Install this skill if you want help making focused browser-game prototypes. Be aware that it may activate for general game-improvement requests, so users should phrase non-browser or non-prototype game questions clearly if they do not want code-generation help.

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
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
95% confidence
Finding

The activation text is broad enough to match many ordinary game-related requests, which can cause the skill to trigger in situations where a narrower or more specialized skill would be more appropriate. Over-broad routing is dangerous because it can unexpectedly steer user requests into a code-generation workflow, increasing the chance of unintended file modifications, scope creep, or misuse of project context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.