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 Paker-kk · Agent Tool · ★ 85
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Flovart safe to install? View the security audit →
Flovart 开源版 Lovart — 自带 Key、接入所有模型、把画布变成 Agent 的运行时 👉 在线体验 Demo 在线体验 • 开始使用 • 功能一览 • 开发计划 这是什么？ 我想要一个真正为 AI 创作而生的画布—— 更自由的模型：BYOK 自带 Key，Google / OpenAI / DeepSeek / MiniMax / 火山引擎 / Qwen 等 12+ Provider 原生接入，再加一层 OpenAI-compatible 中转站适配器，自己接任何端点。 更彻底的工作流：节点流（Workflow）、分镜（Storyboard）、发布审核（P
| Stars | 85 |
| Forks | 22 |
| Language | TypeScript |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 61.7563527656543/100 |
| Open Issues | 4 |
| Last Updated | 2026-05-09 |
| Created | 2025-10-21 |
| Platforms | browser, gemini, node |
| Est. Tokens | ~513k |
These tools work well together with Flovart for enhanced workflows:
Looking for a Flovart alternative? If you're comparing Flovart with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Power rename/refactor tool for CLI and agent use
Explore other popular agent tool tools:
Flovart is Flovart is a web-based infinite canvas inspired by Lovart. It merges flexible drawing tools, a layered workspace and an organized inspiration library with AI-driven image/video generation (via Google . It is categorized as a Agent Tool with 85 GitHub stars.
Flovart is primarily written in TypeScript.
You can find installation instructions and usage details in the Flovart GitHub repository at github.com/Paker-kk/Flovart. The project has 85 stars and 22 forks, indicating an active community.
Flovart is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to Flovart on Agent Skills Hub include tutor-skills, repren. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: