Agent Native

claude-security

Scans your repository for security issues using Claude, examines code changes or commits for vulnerabilities, and generates patch files to fix findings.

by AnthropicOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (anthropics)

Agents
Claude Code
License
LicenseRef-Anthropic-Proprietary (restricted)
Pin
315c4e4pinned Oct 9, 2026
Context cost
about 1,000 tokenswhen the skill loads
GitHub stars
37,546on anthropics/claude-plugins-official
Scripts
None found

What it 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.”
The author's description, from SKILL.md

Generated summary from the skill's own text

Scans your repository for security issues using Claude, examines code changes or commits for vulnerabilities, and generates patch files to fix findings. The skill presents a menu to pick scan scope, runs security analysis with verification, and lets you review before applying any fixes.

When to use it

  • Audit a full codebase for security vulnerabilities and issues
  • Review changes in a branch or pull request for new security risks
  • Generate and review patches to fix identified security findings
  • Check specific commits for introduced security problems

When not to

  • Running untrusted code or scanning repositories you do not own
  • When isolation from repository contents is required for security
  • As a replacement for professional security review or penetration testing

Install

Restricted license: install from the publisher's repository and read its terms.

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add anthropics/claude-plugins-official --skill claude-security

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install anthropics/claude-plugins-official claude-security@315c4e48967d9541c29c3c656441dded353ca7aa

Installs the commit we checked (315c4e4).

Copy by hand

Download the folder at 315c4e4 and put it in .claude/skills/claude-security for Claude Code and in .agents/skills/claude-security for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 315c4e4

Claude Code plugin

/plugin install claude-code-setup@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Claude Code plugin

/plugin install claude-md-management@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Claude Code plugin

/plugin install claude-security@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "claude-security" by Anthropic.

Source, pinned to commit 315c4e48967d9541c29c3c656441dded353ca7aa:
https://github.com/anthropics/claude-plugins-official/tree/315c4e48967d9541c29c3c656441dded353ca7aa/plugins/claude-security/skills/claude-security

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/claude-security/ for Claude Code and .agents/skills/claude-security/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Its license is restricted or not stated. Show me the license terms from the repository before you copy anything.

Listing and checks: https://www.agentnative.dev/skills/anthropic/claude-security

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at 315c4e4

Files

7 files, 137 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 315c4e4
All 50 skills from Anthropic

More from Anthropic

  • receipts

    This skill generates a personal Claude Code usage report from local session transcripts stored in ~/.claude/projects, mining activity across projects without…

    Contains scripts

    Claude Code · about 4.1K tokens · pinned 6 days ago

  • siege

    Orchestrates an iterative proof-finding process for mathematics problems, coordinating multiple rounds of judge and worker agents.

    Contains scripts

    Claude Code · about 18.5K tokens · pinned 6 days ago

  • solo

    This skill enables an agent to work through a single difficult mathematics problem independently within one session.

    Claude Code · about 1.4K tokens · pinned 6 days ago

  • account-context

    Assembles a comprehensive account overview from the CRM, recent emails, documents, call transcripts, and internal chat discussions into a single brief that…

    Claude Code, Codex, Cursor +4 · about 1.8K tokens · pinned 6 days ago

  • ad-manager

    The skill analyzes paid ad performance across TikTok, Google Ads, Facebook, and other platforms via native connectors or CSV exports, explains what is and…

    Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 6 days ago

  • ap-processor

    Reads bills from email, uploads, and expense feeds, extracts vendor and payment details, codes each bill to the owner's chart of accounts and jobs, matches…

    Claude Code, Codex, Cursor +4 · about 3.5K tokens · pinned 6 days ago

All Security skills

Related in Security

  • sensitive-logging-audit

    The skill helps audit and fix sensitive data leaks in Python SDK logging, exceptions, and telemetry by collecting candidate sinks, manually tracing values…

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 970 tokens · pinned 6 days ago

  • security-audit

    This skill guides security audits of codebases, APIs, and services by finding vulnerabilities that cross real trust boundaries.

    by CloudflareOfficial publisher

    Contains scripts

    Claude Code · about 5.4K tokens · pinned 6 days ago

  • assess-patch-risk

    This skill analyzes patch artifacts to assess their program impact, regression risk, and suitability for automated merging.

    by OpenAIOfficial publisher

    Codex · about 2.3K tokens · pinned 6 days ago

  • attack-path-analysis

    This skill analyzes security findings to build explicit attack paths from source to sink, calibrates severity, and decides whether each finding is reportable.

    by OpenAIOfficial publisher

    Codex · about 2.1K tokens · pinned 6 days ago

  • deep-security-scan

    Performs exhaustive, multi-pass security analysis across a repository or scoped directory by running repeated independent security scans and aggregating…

    by OpenAIOfficial publisher

    Codex · about 3.4K tokens · pinned 6 days ago

  • define-security-policy

    This skill helps define or update SECURITY.md files that guide security scanning of repositories.

    by OpenAIOfficial publisher

    Codex · about 1.5K tokens · pinned 6 days ago

Open roles at Anthropic

5 of 178 open roles on the jobs board

See all 178 roles at Anthropic on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use