What security grade does agent-vision-toolkit have?

agent-vision-toolkit is graded SAFE by AgentSkillsHub's rule-based security scan (SlowMist 11 red-flag categories). Reviewed, no blocking issues found — reasonable for general use. Still confirm credential handling before production use.

Is agent-vision-toolkit safe to install?

Security audit of Anionex/agent-vision-toolkit · Codex Skill by Anionex · ★ 1.0k

✓ SAFE Basic audit · rule-based scan · SlowMist 11 red-flag categories

Yes — agent-vision-toolkit passed AgentSkillsHub's rule-based security scan with no dangerous patterns detected. As with any third-party skill, confirm what credentials it requests before production use.

What it is: 为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

No dangerous patterns were detected: no credential exfiltration, no obfuscated downloads, no sandbox-escape attempts, no prompt-injection markers.

Audit summary

Security grade	✓ SAFE
Quality score	74/100
GitHub stars	1.0k
Language	Python
License	MIT
Last updated	2026-08-18

Check before you install

What credentials does it ask for, and where are they stored?
Is the maintainer identifiable and the repo actively maintained?
Read the install scripts and network calls before trusting it.

Run a live scan → Full details & install 5-dimension deep audit

Related Codex Skill audits

Is openclaw safe? — CAUTION · ★ 386.7k
Is hermes-agent safe? — SAFE · ★ 232.7k
Is ui-ux-pro-max-skill safe? — SAFE · ★ 117.9k
Is open-design safe? — SAFE · ★ 89.1k
Is agent-skills safe? — SAFE · ★ 87.3k
Is taste-skill safe? — SAFE · ★ 77.4k

Browse all Codex Skill skills →

This is AgentSkillsHub's free basic audit: an automated rule-based scan covering SlowMist's 11 red-flag categories (credential exfiltration, obfuscated payloads, sandbox escape, prompt injection, and more) across 130,000+ open-source AI agent skills and MCP servers, refreshed every 8 hours. A SAFE grade is a scan result, not a guarantee — deep 5-dimension audits (code · credentials · vendor · supply-chain · operational) are available for enterprise. Audited: 2026-08-19.