ClawHub
Back to skill

Security audit

GPT Image 2 文生图

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI Hive text-to-image helper with expected API-key handling and no evidence of hidden, destructive, or unrelated behavior.

Install only if you are comfortable giving this helper an AI Hive API key, storing that key locally in ~/.ai-hive/config.json, sending prompts to AI Hive, and saving generated outputs to your Downloads folder or another chosen directory. Use a scoped or revocable API key if AI Hive supports it.

SkillSpector

By NVIDIA
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
88% confidence
Finding
The skill invokes shell commands, performs network access, reads environment-derived paths, and writes a local config file, yet it declares no permissions or trust boundaries. This is dangerous because users and host systems cannot accurately assess or constrain what the skill can do, increasing the risk of unintended key storage, external data transmission, or broader tool misuse.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The skill is presented as a simple text-to-image generator, but it also initializes credentials, opens AI Hive for key acquisition, stores API keys locally, and allows querying task status by arbitrary task ID. That mismatch is dangerous because users may consent to image generation without realizing the skill performs credential handling and broader account-linked API operations, which can expose secrets or permit access to unrelated tasks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.