The 15 Best Claude Code Skills for Security
Ranked by quality, maintenance and a safety scan of every file · Updated
Skills for security review, vulnerability hunting, audits and secure coding. We compared 51 Claude Code Skills for Security that pass our quality bar, 96% of which came up clean on our safety scan; these are the top 15, no more than three from any one repository.
- 1
plugin-audit
by alirezarezvani
Run the full 8-phase plugin audit pipeline on a skill directory.
Quality 95/100Safety scan clean★ 29,782Updated 4 days agoWhy it is here: updated 4 days ago; clean safety scan; 29,782 GitHub stars.
npx skills add alirezarezvani/claude-skills - 2
agentic-test-audit
by sickn33
Audit a pytest suite: surviving mutants and untested code, flaky, order-dependent and slow tests, and removal candidates checked on held-out mutants. Report-only.
Quality 97/100Safety scan clean★ 49,671Updated 3 days agoWhy it is here: highest quality score in this list; updated 3 days ago; clean safety scan.
npx skills add sickn33/agentic-awesome-skills --skill agentic-test-audit - 3
agenttrace-session-audit
by sickn33
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
Quality 95/100Safety scan clean★ 49,671Updated 3 days agoWhy it is here: updated 3 days ago; clean safety scan; 49,671 GitHub stars.
npx skills add sickn33/agentic-awesome-skills --skill agenttrace-session-audit - 4
signed-audit-trails-recipe
by wshobson
Step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls
Quality 95/100Safety scan clean★ 39,920Updated 57 days agoWhy it is here: clean safety scan; 39,920 GitHub stars.
npx skills add wshobson/agents --skill signed-audit-trails-recipe - 5
seo-audit
by AgriciDaniel
Run a full-site SEO audit and return a scored, prioritized report. Use only for site-wide checks; use seo-page for one URL or seo-technical for a technical-only review.
Quality 96/100Safety scan clean★ 29,294Updated 2 days agoWhy it is here: updated 2 days ago; clean safety scan; 29,294 GitHub stars.
npx skills add AgriciDaniel/claude-seo --skill seo-audit - 6
ai-coding-agent-guardrails
by sickn33
Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission
Quality 97/100Safety scan clean★ 49,671Updated 3 days agoWhy it is here: highest quality score in this list; updated 3 days ago; clean safety scan.
npx skills add sickn33/agentic-awesome-skills --skill ai-coding-agent-guardrails - 7
apify-security-basics
by jeremylongshore
Secure Apify API tokens, configure proxy access, and protect Actor data. Use when hardening API key management, setting up environment-specific tokens, rotating a leaked token, or auditing Apify security configuration.
Quality 87/100Safety scan clean★ 2,785Updated 53 days agoWhy it is here: clean safety scan; 2,785 GitHub stars.
npx skills add jeremylongshore/tons-of-skills-marketplace --skill apify-security-basics - 8
seo-audit
by Ryze-AI-Adgent
Full SEO audit of a site from its real Search Console + GA4 data — indexation health, CTR anomalies, decaying pages, striking-distance keywords, quick wins
Quality 84/100Safety scan clean★ 9,792Updated 20 days agoWhy it is here: updated 20 days ago; clean safety scan; 9,792 GitHub stars.
npx skills add Ryze-AI-Adgent/open-seo-mcp-skills --skill seo-audit - 9
alchemy-security-basics
by jeremylongshore
Analyze and secure Alchemy credentials, browser access, wallet authority, webhook verification, and untrusted chain data
Quality 83/100Safety scan clean★ 2,785Updated 53 days agoWhy it is here: clean safety scan; 2,785 GitHub stars.
npx skills add jeremylongshore/tons-of-skills-marketplace --skill alchemy-security-basics - 10
blog-locale-audit
by AgriciDaniel
Read-only audit of a folder of existing multilingual blog posts: translation coverage, parity, hreflang and canonical consistency, meta-tag parity, and stale translations, with a prioritized report
Quality 91/100Safety scan clean★ 2,655Updated 14 days agoWhy it is here: updated 14 days ago; clean safety scan; 2,655 GitHub stars.
npx skills add AgriciDaniel/claude-blog --skill blog-locale-audit - 11
agentic-actions-auditor
by trailofbits
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference.
Quality 89/100Safety scan clean★ 7,225Updated 54 days agoWhy it is here: clean safety scan; 7,225 GitHub stars.
npx skills add trailofbits/skills --skill agentic-actions-auditor - 12
09-web-security
by Masriyan
OWASP Top 10 testing, injection vulnerability detection, API security
Quality 88/100Safety scan clean★ 441Updated 2026-09-07Why it is here: clean safety scan.
npx skills add Masriyan/Claude-Code-CyberSecurity-Skill --skill 09-web-security - 13
02-vulnerability-scanner
by Masriyan
Dependency auditing, CVE detection, configuration security review, CVSS
Quality 87/100Safety scan clean★ 441Updated 2026-09-07Why it is here: clean safety scan.
npx skills add Masriyan/Claude-Code-CyberSecurity-Skill --skill 02-vulnerability-scanner - 14
abridge-security-basics
by jeremylongshore
Review Abridge deployment controls across data handling, identity, devices, EHR workflows, support, auditability, and incident response
Quality 87/100Safety scan clean★ 2,785Updated 53 days agoWhy it is here: clean safety scan; 2,785 GitHub stars.
npx skills add jeremylongshore/tons-of-skills-marketplace --skill abridge-security-basics - 15
ai-coding-agent-guardrails
by BagelHole
Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.
Quality 88/100Safety scan clean★ 1,113Updated 2026-05-22Why it is here: clean safety scan; 1,113 GitHub stars.
npx skills add BagelHole/DevOps-Security-Agent-Skills --skill ai-coding-agent-guardrails
Side by side
| # | Name | Quality | Safety | Stars | Updated |
|---|---|---|---|---|---|
| 1 | plugin-audit | 95 | Clean | 29,782 | 4 days ago |
| 2 | agentic-test-audit | 97 | Clean | 49,671 | 3 days ago |
| 3 | agenttrace-session-audit | 95 | Clean | 49,671 | 3 days ago |
| 4 | signed-audit-trails-recipe | 95 | Clean | 39,920 | 57 days ago |
| 5 | seo-audit | 96 | Clean | 29,294 | 2 days ago |
| 6 | ai-coding-agent-guardrails | 97 | Clean | 49,671 | 3 days ago |
| 7 | apify-security-basics | 87 | Clean | 2,785 | 53 days ago |
| 8 | seo-audit | 84 | Clean | 9,792 | 20 days ago |
| 9 | alchemy-security-basics | 83 | Clean | 2,785 | 53 days ago |
| 10 | blog-locale-audit | 91 | Clean | 2,655 | 14 days ago |
| 11 | agentic-actions-auditor | 89 | Clean | 7,225 | 54 days ago |
| 12 | 09-web-security | 88 | Clean | 441 | 2026-09-07 |
| 13 | 02-vulnerability-scanner | 87 | Clean | 441 | 2026-09-07 |
| 14 | abridge-security-basics | 87 | Clean | 2,785 | 53 days ago |
| 15 | ai-coding-agent-guardrails | 88 | Clean | 1,113 | 2026-05-22 |
How we rank
Only skills we have read make the list: the file itself was fetched, it has a real description, it scores at least 55 of 100 on quality, its source still exists, its repository has at least 20 GitHub stars, and our safety scan found nothing high-risk. The order then follows adoption (GitHub stars, on a log scale), how squarely it fits this topic, and its quality score (how substantial and well structured the file is and how recently it changed), moved up for a clean safety scan and for real installs through the SkillAgent MCP server, and down for safety notes. At most three come from any one repository, and tools sold on evading bot detection are never listed. We do not rank by install counts reported by a command-line tool: they are easy to inflate, and our research found repositories with no stars claiming hundreds of thousands of installs. The list is recomputed on every visit.
Questions
What is the best Claude Code Skill for Security?
plugin-audit by alirezarezvani ranks first: updated 4 days ago, clean safety scan, 29,782 GitHub stars. The full ranking above lists 15 alternatives with their trade-offs.
How do I install one?
Each entry shows a one-line command. `npx skills add` installs a skill for Claude Code, Cursor, Codex, Gemini CLI and other agents that read skill files.
Are these safe to install?
Every file is scanned for instructions that work against you: hidden text, data sent to outside servers, disabled approval prompts, leaked keys. Skills with a warning are never listed here, and 96% of the 51 we compared for this guide came up clean. Read a skill before installing it all the same: it runs with your permissions.