mmx-cli
Generate Media with MiniMax CLI
Multimodal content creation often requires separate tools for text, images, video, speech, music, and search. This skill guides agents through mmx CLI commands for MiniMax workflows.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "mmx-cli" from https://skillstore.io/skills/minimax-ai-mmx-cli.md and its manifest at https://skillstore.io/api/skills/minimax-ai-mmx-cli/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "mmx-cli". Generate a 16:9 hero image of a clean robotics lab.
Expected outcome:
The skill returns MiniMax image result URLs or saved file paths, depending on the requested output mode.
Using "mmx-cli". Create a short ocean waves video and save it locally.
Expected outcome:
The workflow starts a video task, checks completion status, and saves the completed video file path.
Using "mmx-cli". Turn a product announcement into narrated audio.
Expected outcome:
The skill produces an MP3 file path and can include subtitle timing information when requested.
Security Audit
High RiskMost static command findings are false positives from Markdown code spans, fenced bash examples, and documented mmx CLI flags. Confirmed risk remains around MiniMax credential persistence, command-line API key exposure, global npm installation, and third-party data transfer. No prompt injection attempt was found in SKILL.md.
Confirmed security concerns (4)
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (126)
📁 Filesystem access (5)
🔑 Env variables (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/minimax-ai-mmx-cli/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/minimax-ai-mmx-cli?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/minimax-ai-mmx-cli?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/minimax-ai-mmx-cli/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/minimax-ai-mmx-cli.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
MiniMax-AI. (2026). mmx-cli security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/minimax-ai-mmx-cli/audits/5BibTeX citation
@techreport{minimax-ai-minimax-ai-mmx-cli-2026,
author = {MiniMax-AI},
title = {mmx-cli security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/minimax-ai-mmx-cli/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "mmx-cli security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "MiniMax-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/minimax-ai-mmx-cli/audits/5"
identifiers:
- type: other
value: "skillstore:minimax-ai-mmx-cli:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Produce Campaign Media
Create images, short videos, narration, and background music from approved creative prompts.
Automate Agent Workflows
Use JSON output, non-interactive flags, and exported schemas to connect MiniMax commands to agent pipelines.
Analyze and Search Visual Context
Describe images, query MiniMax search, and combine results with generated content tasks.
Try These Prompts
Use mmx-cli to generate one 16:9 image from this prompt: [prompt]. Return the saved path or result URLs.
Use mmx-cli to synthesize this script with voice [voice]. Save an MP3 file and report the output path: [script].
Start an async video generation task for [scene], poll the status, and download the final video to [path]. Use quiet JSON output.
Export the mmx schema for [command or all commands], inspect required arguments, and propose a safe agent tool plan.
Best Practices
- Use non-interactive, quiet, and JSON output flags for agent and CI runs.
- Get user approval before uploading local files, private prompts, or generated media.
- Avoid command-line API keys in shared environments; use secure credential storage instead.
Avoid
- Passing real API keys in chat prompts, shell history, or shared logs.
- Uploading confidential images, documents, scripts, or lyrics without explicit approval.
- Installing or updating global CLI packages in production agents without review.
Frequently Asked Questions
What does this skill help automate?
Does it require a MiniMax account?
Can it save generated media files?
Is it compatible with Claude, Codex, and Claude Code?
Does it send data to a third-party service?
What should users review before using it?
Developer Details
Author
MiniMax-AILicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
4 downloads · 93 views
File structure
📄 SKILL.md