ClawHub
Back to skill

Security audit

ZenMux Image Gen (Nano Banana 2)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ZenMux image-generation wrapper that sends prompts and optional images to ZenMux and saves returned images locally.

Install only if you are comfortable sending image prompts and any selected input images to ZenMux. Use the ZENMUX_API_KEY environment variable rather than passing keys on the command line, and avoid using confidential images or prompts unless ZenMux's data handling terms are acceptable to you.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation describes capabilities that require access to environment variables and outbound network calls, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates a mismatch between documented behavior and declared execution boundaries, which can lead to overbroad runtime access, poor reviewability, and unintended secret or network use if the platform does not enforce least privilege by default.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends the user's prompt and optional input image to the remote ZenMux API, but the only indication is implicit in the tool's purpose and code flow, not an explicit runtime disclosure or consent check. This can expose sensitive text or local image contents to a third party, which is a real privacy/security concern if users invoke the skill assuming processing is local or do not realize uploaded images may contain confidential data.

Static analysis

No suspicious patterns detected.