Security audit

GPT Image 2 图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed AI Hive image-generation skill that uploads user-chosen media and stores an API key, with no evidence of hidden exfiltration, destructive behavior, or automatic broad local access.

Install only if you are comfortable using the third-party AI Hive service, storing an AI Hive API key locally, and uploading the specific images or media you provide to that service. Avoid passing private files as references unless you intend to upload them.

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill declares no permissions, yet the documented commands clearly imply shell execution, network access, environment use, and file read/write. This creates a transparency and governance gap: operators may invoke the skill without understanding that it can install packages, upload local files, download outputs, and interact with external services.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The skill is presented as a GPT Image 2 image-generation/editing wrapper, but the underlying behavior reportedly includes chat, video generation, user/account queries, model enumeration, generic media upload, and browser-driven API key setup. That mismatch is dangerous because users and reviewers may authorize the skill for a narrow use case while it exposes far broader data access and action surfaces than advertised.

Static analysis

No suspicious patterns detected.