OpenAI · Agent Skill

security-best-practices

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python,…

Published by OpenAI86 lines in SKILL.md
Source
openai/skills/skills/.curated/security-best-practices
Repository owner
openai

Install

Read the SKILL.md and any scripts before installing: a skill runs with your agent's permissions. This copies just this skill into Claude Code's user skills folder; other agents read skills from their own folder.

Claude Code (user-level)

git clone --depth 1 --filter=blob:none --sparse https://github.com/openai/skills.git /tmp/skills
cd /tmp/skills && git sparse-checkout set "skills/.curated/security-best-practices"
mkdir -p ~/.claude/skills && cp -r "skills/.curated/security-best-practices" ~/.claude/skills/security-best-practices

Skills folder docs:

Claude CodeCodexGemini CLIOpenCodeCursorGitHub CopilotgooseOpenHandsAmpFactory DroidJunieKiroRoo CodeMistral VibepiHermes AgentOpenClawLetta

Works with

Agent Skills is an open format, so this skill loads in any harness that supports it, including Claude Code, Codex, Gemini CLI, OpenCode, Cursor, GitHub Copilot, goose, OpenHands. Some skills are written for one product and say so in their description.

More skills from OpenAI

aspnet-corechatgpt-appscli-creatorcloudflare-deploydefine-goalfigmafigma-code-connect-componentsfigma-create-design-system-rulesfigma-create-new-filefigma-generate-designfigma-generate-libraryfigma-implement-design

Reviewed Oct 5, 2026. Name and description are the skill's own frontmatter.