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 Anionex · Codex Skill · ★ 272
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-vision-proxy safe to install? View the security audit →
codex-vision-proxy formerly 🌐 中文 ｜ English If your Codex is already connected to DeepSeek, but you're frustrated that the model has no multimodal ability — it can't see images, and every attempt to look at an image is blocked by the system — this repository offers a way to let a text-only model call Codex's built-in without errors. Instead of failing, it returns a detailed description of the image, keeping the text-only model's experience as close as possible to a multimodal one, without introducing extra MCPs, skills, or CLIs, and without the risk of repeated configuration. It also provides an optional vision toolkit that leverages multimodal models for image Q&A, OCR, visual grounding, and more. All code has been verified in real Codex + DeepSeek sessions. Use cases include but are not limited to: image Q&A, screenshot analysis, Computer Use GUI operation, and multi-step image reasoning. If the agent you're using isn't Codex, you can also try installing the visual toolkit from this repository — it provides CLIs that let agents interact with images. If this project helps you, feel free to star🌟 & follow～ I'll keep sharing more practical tools and tips. Real-world Effects <img s
| Stars | 272 |
| Forks | 12 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 74.5871547016987/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-04 |
| Created | 2026-08-01 |
| Platforms | codex, python |
| Est. Tokens | ~15k |
These tools work well together with codex-vision-proxy for enhanced workflows:
Looking for a codex-vision-proxy alternative? If you're comparing codex-vision-proxy 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.
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Curs
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an
Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关，提供权重负载均衡、可观测性与费用追踪
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Explore other popular codex skill tools:
codex-vision-proxy is 让纯文本模型在 Codex 中无障碍看图(view_image)的更优方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ A superior approach for enabling text-only models to seamlessly use Codex’s built-in view_image, plus a vision toolkit & skill designe. It is categorized as a Codex Skill with 272 GitHub stars.
codex-vision-proxy is primarily written in Python. It covers topics such as agent, agent-skills, codex.
You can find installation instructions and usage details in the codex-vision-proxy GitHub repository at github.com/Anionex/codex-vision-proxy. The project has 272 stars and 12 forks, indicating an active community.
codex-vision-proxy is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-vision-proxy on Agent Skills Hub include modsearch, sub-agents-skills, entroly. 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: