codex-canvas — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Xiangyu-CAS · Codex Skill · ★ 132

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is codex-canvas safe to install? View the security audit →

About codex-canvas

Codex-Canvas English 日本語 Codex-Canvas is an infinite canvas plugin for Codex. It requires no API setup and uses Codex's built-in GPT-image-2 workflow to edit images on a local canvas. It opens directly inside Codex, collects generated images into the current project, and lets you organize, annotate, edit, compare, and reuse visual assets. It brings a Lovart-like workflow to Codex: chat on one side, canvas on the other, with powerful image editing tools designed around the same creative loop. Installation Copy this prompt into Codex: See the full installation guide in . Stable versions ship through GitHub Releases. Settings → Version only installs a release after its assets are complete and its manifest matches the tag, never unreleased commits from . The old server exits after an update; reopen the canvas and start a new Codex task. After installation, start a new Codex task and open the canvas: Roadmap [x] GPT-image-2 powered image editing [ ] Editable PPT generation and export

codexgpt-image-2infinite-canvaslovartskills

Quick Facts

Stars132
Forks16
LanguageJavaScript
CategoryCodex Skill
LicenseMIT
Quality Score70.7521714832874/100
Open Issues4
Last Updated2026-10-01
Created2026-07-01
Platformscodex, node
Est. Tokens~15k

codex-canvas alternative? Top 6 similar tools

Looking for a codex-canvas alternative? If you're comparing codex-canvas with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ilab-gpt-conjure by kadevin · ⭐ 625

    面向 GPT-image-2 的 AI 图片生成 WebUI 工作台,支持 Codex Responses 与 OpenAI 兼容 API 接入,内置公用图库、多类型 Chip 快捷引用、提示词模板、多任务并发和本地队列

  • agnix by agent-sh · ⭐ 430

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • skillport by gotalab · ⭐ 406

    Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

  • mcp-image by shinpr · ⭐ 168

    MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Support

  • gpt-image-2-skill by Wangnov · ⭐ 143

    GPT Image 2 Skill / CLI / Web / Desktop

  • Iris by avabbbb · ⭐ 139

    Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is codex-canvas?

codex-canvas is Infinite canvas plugin for codex; Codex无限画布插件,图层分离,涂抹修改. It is categorized as a Codex Skill with 132 GitHub stars.

What programming language is codex-canvas written in?

codex-canvas is primarily written in JavaScript. It covers topics such as codex, gpt-image-2, infinite-canvas.

How do I install or use codex-canvas?

You can find installation instructions and usage details in the codex-canvas GitHub repository at github.com/Xiangyu-CAS/codex-canvas. The project has 132 stars and 16 forks, indicating an active community.

What license does codex-canvas use?

codex-canvas is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to codex-canvas?

The top alternatives to codex-canvas on Agent Skills Hub include ilab-gpt-conjure, agnix, skillport. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools