Claude Security
Claude Security is an agent skill (a SKILL.md file) from anthropics/claude-plugins-official. Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings… It works with Claude Code and has 47,414 GitHub stars across a repository of 7 listed skills.
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
- Official
- Multi-skill repo
- Plugin marketplace
- Security
- Maintained
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add anthropics/claude-plugins-official
/plugin install claude-security@claude-plugins-officialIn the Claude apps, zip the claude-security folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git
cp -r claude-plugins-official/plugins/claude-security/skills/claude-security .agents/skills/claude-security # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git
cp -r claude-plugins-official/plugins/claude-security/skills/claude-security .cursor/skills/claude-security # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose). Use when the user asks to scan, audit or check code with Claude Security, to scan their changes with Claude Security, or to fix or patch Claude Security findings. This is the front desk.
When it triggers
- Use when the user asks to scan, audit or check code with Claude Security, to scan their changes with Claude Security, or to fix or patch Claude Security findings.
More skills in anthropics/claude-plugins-official
7 skills are listed from this repository.
Breakdown Diagnosisanthropics/claude-plugins-official
Claude Automation Recommenderanthropics/claude-plugins-official
Claude Md Improveranthropics/claude-plugins-official
Customer Inquiry Intakeanthropics/claude-plugins-official
Morning Plant Pulseanthropics/claude-plugins-official
Trade Study Reportanthropics/claude-plugins-official
Similar skills
More security skills
Accesslint Audit
sickn33/agentic-awesome-skills
Find and fix WCAG 2.2 accessibility issues.
Active · last commit Nov 15, 2026
SecurityPythonResume Builder
reactive-resume/reactive-resume
Builds a complete resume as Reactive Resume JSON that conforms to the schema and imports at https://rxresu.me.
Active · last commit Nov 15, 2026
SecurityTypeScriptGws Admin Reports
googleworkspace/cli
Google Workspace Admin SDK: Audit logs and usage reports.
Maintained · last commit Oct 30, 2026
SecurityRustAgent Owasp Compliance
github/awesome-copilot
Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks.
Maintained · last commit Nov 16, 2026
OfficialSecurityJavaScriptAnalyzing Indicators Of Compromise
mukul975/Anthropic-Cybersecurity-Skills
Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority.
Active · last commit Aug 31, 2026
SecurityPythonOmp Roles
agentscope-ai/QwenPaw
Use this skill whenever you need the allowedtools / skills preset for a sub-agent role before calling spawnsubagent.
Active · last commit Nov 16, 2026
SecurityTypeScript
How do I install the Claude Security skill?
In Claude Code, run /plugin marketplace add anthropics/claude-plugins-official and then /plugin install claude-security@claude-plugins-official. For Codex or Cursor, copy the claude-security folder into .agents/skills/ or .cursor/skills/.
Is the Claude Security skill free?
Yes. The repository is open source under the Apache-2.0 license.
Is Claude Security maintained?
The repository's most recent commit was on Nov 14, 2026. appsgit only lists skills from repositories with a commit in the last six months.