ClawHub
Back to skill

Security audit

Chatgpt Image Gen

Security checks for vulnerabilities and agentic risk

Overview

The skill is an image-generation helper, but it tells the agent to automate a logged-in ChatGPT browser session and explicitly frames that as bypassing bot detection.

Install only if you intentionally want OpenClaw to control your logged-in ChatGPT tab for image generation. Treat it as account-level browser automation: review prompts before submission, keep the relay attached only when needed, and prefer official or built-in image-generation paths when available. The main concern is not hidden code, but the explicit bot-detection bypass framing and broad authority of a real browser session.

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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The invocation guidance is very broad ('use when the user wants to create images') and does not clearly limit when this skill should be selected versus safer built-in or official API-based approaches. In context, that broad trigger increases the chance the automation is invoked unnecessarily against a live logged-in browser session, expanding exposure to unintended actions or policy-violating use.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs users to use an attached real browser session to 'bypass ChatGPT's bot detection,' which is guidance for evading a platform security/abuse-control mechanism. Even though it relies on the user's own logged-in session rather than stolen credentials, it normalizes anti-detection behavior and enables automation to act with the full privileges of the user's account.

Static analysis

No suspicious patterns detected.