ClawHub
Back to skill

Security audit

GT7 Tuner — Gran Turismo 7 AI Tuning Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed GT7 tuning helper that uses a third-party tuning website for its intended purpose, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install this only if you are comfortable with an agent using your GT Pro Tune account and possibly uploading GT7 screenshots to that service. Confirm before login or upload, and do not use it for general GT7 advice unless you actually want the automated GT Pro Tune workflow.

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
94% confidence
Finding

The skill activates on very broad GT7-related phrases such as general tuning discussion, screenshots, or mentions of setup topics, which can cause the agent to enter a browser-automation workflow without sufficiently specific user intent. In this skill, broad triggering is more concerning because the downstream flow includes use of stored third-party credentials and navigation to an external web app, increasing the chance of unnecessary credentialed actions or accidental data handling.

Content

No source excerpt is available for this finding.