Harness Security Bench

Q: What is a Claude Code skill and how does the Harness Security Bench skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Harness Security Bench is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at https://claudskills.com/learn/what-is-skill-md/.

Category: Security · Sub-category: security-misc · Last updated: 2026-06-22

ai:llm

Run `@metaharness/darwin security bench` (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-pass, B2 fixed-agent, B3 Darwin-champion). Closest reference implementation for ruflo's own ADR-155 nightly self-learning security harness (PR #2417). Degrades gracefully when @metaharness/darwin is absent.

Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

Surfaces the upstream metaharness-darwin security bench command. This is the upstream's own ADR-155 — Darwin Shield — and is the closest reference implementation for ruflo's nightly self-learning security harness ([#2417](https://github.com/ruvnet/ruflo/pull/2417)).

What this skill does

Harness Security Bench is a community-contributed Claude Code skill in the security-misc sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/harness-security-bench/ and loads when your prompt matches the skill's trigger.

Who uses this skill

The Harness Security Bench Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 146,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/harness-security-bench
curl -L https://claudskills.com/skills/harness-security-bench/SKILL.md \
  -o ~/.claude/skills/harness-security-bench/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/harness-security-bench/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/harness-security-bench/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\harness-security-bench\SKILL.md on Windows. See the full install guide for step-by-step instructions.

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

See pricing → Download desktop app

Frequently asked questions

How do I install the Harness Security Bench Claude Code skill?

Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/harness-security-bench/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.

What does the Harness Security Bench skill do?

Is this skill free to install?

Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.

When should I use the Harness Security Bench skill?

Use Harness Security Bench when your Claude Code task falls under the Security category — specifically in the security misc area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Harness Security Bench" or describe the task and let Claude pick). Browse related skills at /category/security/.

What is a Claude Code skill and how does the Harness Security Bench skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Harness Security Bench is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Source: https://github.com/ruvnet/ruflo/blob/HEAD/plugins/ruflo-metaharness/skills/harness-security-bench/SKILL.md
License: MIT
Author: ruvnet
Website: https://Cognitum.One

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA

ruvnet. (2026). Harness Security Bench [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/harness-security-bench/

BibTeX

@misc{harness-security-bench-2026,
  author    = {ruvnet},
  title     = {Harness Security Bench [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/harness-security-bench/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge

[![ClaudSkills](https://claudskills.com/badge/harness-security-bench.svg)](https://claudskills.com/skills/harness-security-bench/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)

Security scan

Grade A · scanned 2026-07-06 — free static scan against the OWASP Agentic Skills Top 10.

The scan flagged 1 of 10 categories (filesystem), including lower-severity patterns. Patterns shown inside code fences are weighted as examples rather than instructions — read the grading methodology for what this does and does not guarantee.

✓ Prompt injection
✓ Data exfiltration
✓ Supply chain
✓ Reverse shell
✓ Credentials
✓ Execution
⚠ Filesystem
✓ Persistence
✓ Obfuscation
✓ Network

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/harness-security-bench/#security)

More Security skills

Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all Security skills → Top 100 skills

Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills. · What's New · Install guide · About · llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore