ZenMux Image Generation

• Outcome: Pass
• Latest audit: May 28, 2026, 12:10 PM
• Version:
  1.5.0

Overview

This skill appears to do what it claims: use ZenMux to generate images, while sending your prompt and any chosen reference images to that service.

Install this only if you intend to use ZenMux for cloud image generation. Use a revocable ZenMux API key, avoid submitting confidential, regulated, or personal images unless ZenMux's policies are acceptable to you, and choose the output path carefully because the script writes the generated image there.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill documentation describes use of an environment variable API key and outbound requests to ZenMux, but it does not declare permissions corresponding to those capabilities. This creates a transparency and governance gap: users and platforms cannot accurately assess that the skill accesses secrets and communicates with an external service before use.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill instructs users to provide prompts and reference images to a third-party API but does not clearly disclose that this content will leave the local environment and be transmitted to ZenMux. This can lead to unintentional disclosure of sensitive text, personal images, or proprietary material, especially because image-to-image and multi-image fusion workflows encourage uploading user-supplied files.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The script transmits the user prompt and the full contents of local image files to a third-party remote API, but it provides no explicit disclosure, confirmation, or privacy guardrails before upload. In an agent-skill context, this can cause unintended disclosure of sensitive local files or confidential prompts if the caller does not understand that local content will leave the host.

VirusTotal

66/66 vendors flagged this skill as clean.