ClawHub
Back to skill

Security audit

Nano Banana Pro 图片工作室｜AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This is a purpose-aligned AI-HIVE image-generation skill with disclosed API, upload, download, and local key-storage behavior, but users should review broad activation and paid-generation steps carefully.

Install this if you intend to use AI-HIVE for image generation or editing. Before running commands, review the model, routing mode, price snapshot, output directory, and every media path that will be uploaded. Keep the API key out of chat, logs, screenshots, and repositories, and confirm you have rights to any reference assets you provide.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill documentation includes executable examples and operational behavior implying access to environment variables, local files, shell commands, and outbound network calls, yet no explicit permission declaration is present. This creates a transparency and least-privilege problem: users or platforms may invoke a skill with broader capabilities than expected, increasing the chance of secret exposure, unintended file access, or external requests without clear consent boundaries.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger conditions are very broad and include generic terms such as '图片生成', '图片编辑', '商品图', and '广告图', which can cause the skill to activate for many ordinary requests beyond its specialized intended scope. Over-broad invocation increases the risk of unnecessary access to image-generation workflows, user materials, or billable API paths in situations where a simpler or safer tool should have been used.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill enables implicit invocation but does not define narrow trigger conditions, so the agent may auto-activate this skill in broader contexts than intended. Because the skill can generate runnable AI-HIVE commands and perform image-generation/editing workflows, accidental invocation could cause unintended external actions, cost-incurring operations, or policy-sensitive content processing without clear user intent.

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
The default prompt hard-codes production-ready Chinese output without indicating that this is user-selectable, which can override user language expectations and reduce transparency about what the skill will do. In a workflow that produces runnable commands and delivery materials, forced language can increase operator error, misunderstandings, or missed review of sensitive instructions, though it is not by itself a severe security flaw.

Static analysis

No suspicious patterns detected.