ClawHub
Back to skill

Security audit

Nano Banana Pro 营销图片

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI Hive marketing-image workflow, with some broader leftover helper code that is not exposed in the documented runtime path.

Install only if you are comfortable using AI Hive, storing an API key under ~/.ai-hive/config.json, and uploading selected reference images/media to the AI Hive service. Avoid pointing the upload or image arguments at private files unrelated to the marketing assets you intend to generate.

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
94% confidence
Finding
The skill declares no permissions, yet its documented commands and referenced helper script imply shell execution, network access, environment use, and file read/write. This creates a capability-transparency failure: users and policy layers cannot accurately assess or constrain what the skill can do, increasing the chance of unintended data access, exfiltration, or unsafe command execution.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill is presented as a narrowly scoped marketing-image generator, but static analysis indicates the underlying tooling exposes much broader capabilities such as generic chat, video generation, media upload, model enumeration, wallet/user-info queries, and interactive API-key setup. This mismatch is dangerous because operators may invoke or approve the skill under false assumptions, while the embedded toolchain can perform unrelated sensitive actions outside the declared business purpose.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.