ClawHub
Back to skill

Security audit

Nano Banana 2 图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed AI Hive image-generation helper that uploads user-selected media, submits generation jobs, and downloads results as expected for its purpose.

Install only if you are comfortable sending prompts and any chosen reference images to AI Hive. Use --no-download or a specific --output-dir when appropriate, and keep the stored API key protected or use AI_HIVE_API_KEY if you prefer not to write a config file.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill declares no permissions while the documented commands clearly imply shell execution, network access, environment use, and filesystem read/write for uploading images, installing dependencies, and downloading outputs. This creates a transparency and least-privilege problem: users and orchestrators cannot accurately assess what the skill will access before invocation.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The description includes broad trigger phrases covering many common image-generation and editing requests, which can cause the skill to be selected in contexts beyond its narrowly intended use. Over-broad invocation increases the chance that a network/file-capable skill is auto-invoked on generic user requests, exposing files or sending data to external services unnecessarily.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill content is written to enforce Chinese-language instructions/output without indicating user choice. This can mis-handle user intent, obscure security-relevant notices or consent prompts for non-Chinese users, and make it harder for users to verify what external actions the skill is taking.

Static analysis

No suspicious patterns detected.