← All skills

threat-model-visualize

97 / 100 · Low risk

Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By openai/codex-security (GitHub) · security · 11,339 stars · scanned at commit 884b7b6

Turn an existing threat model into an interactive architecture and threat-path explorer. Resolve simple requests for a target's last scan; do not perform a new assessment.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'threat-model-visualize' ] || [ -L ~/.agents/skills/'threat-model-visualize' ]; then echo 'A skill folder named threat-model-visualize already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/openai/codex-security' "$d" && git -C "$d" checkout --quiet '884b7b657a1d8738c50d1967d309cab37c9380a7' -- 'plugins/codex-security/skills/threat-model-visualize' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/codex-security/skills/threat-model-visualize' ~/.agents/skills/'threat-model-visualize' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'threat-model-visualize' ~/.claude/skills/'threat-model-visualize' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for openai/codex-security shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/openai/codex-security.svg)](https://zalavijaysinh.github.io/skilltrust/repos/openai/codex-security/)

Score history