awesome-security-agent-harnesses

Awesome Security Agent Harnesses AI agents for pentesting, code audit, fuzzing, vulnerability discovery, and reverse engineering: harnesses, sandboxes, security MCP servers, benchmarks, and evals.

Explore the papers, code, and people behind security agents. Which papers and benchmarks should you explore next?

This list is a starting point. I built Papers With Code Cyber to make the wider collection easier to explore: cybersecurity papers, engineering posts, and repositories you can filter by topic, target, and contribution—with organizations and developers connected to their work.

Built on Hugging Face’s open-source Papers with Code, focused on cybersecurity agent harnesses.

Watch the full 55-second demo

Explore the live catalog → · Connect your agent through MCP — no account or API key required.

Open source & contributions Suggest a paper, post, or repository: contribute to this awesome list or request a catalog addition. Improve the tools: bugs, feature requests, and PRs welcome in the website/API and MCP/CLI repositories.

Please read the contribution guidelines before opening a pull request.

Building or studying security agent harnesses? Join the Discord to trade notes, benchmark results, and new finds. Contents What Is a Security Agent Harness Code Audit Harnesses Pentesting Agents Fuzzing and Vulnerability Discovery DARPA AIxCC Cyber Reasoning Systems Agent Tooling and Integrations Agent Sandboxes Benchmarks and Evals Readings What Is a Security Agent Harness

A security agent harness is everything wrapped around the model: the sandbox it runs in, the analysis tools it can call, the prompts and skills that encode a methodology, and the evals you use to check it. Most of the engineering lives here rather than in the model, or as Cloudflare put it after scaling one across its own fleet, the harness is the bit that lasts.

Agents are good at producing plausible findings and bad at telling which ones are real. An agent will edit the source so its own exploit works, then report the bug it just created. So the metric that matters is not recall, which nobody can measure without already knowing every bug in a codebase, but how few unconfirmed findings reach a human: Cloudflare's pipeline cut 20,799 raw candidates down to 12,057 that survived validation, then folded away another 5,442 as duplicates. A harness that can reproduce a crash, replay an input, or re-run a static analyzer is how you throw out the bad ones before a human ever sees them.

Entries tagged SKILL.md are skill packs rather than runnable harnesses: methodology encoded as Agent Skills that a general coding agent like Claude Code executes. They live in the section matching what they do. Code Audit Harnesses

Harnesses that run coding agents against source code: discovery, triage, validation, and patching. 0 Security - Security harness with a local web console for vulnerability research, verification, and fixes, exposing the same reusable workflows through CLI and MCP. Anthropic Defending Code Reference Harness - Reference implementation for autonomous vulnerability discovery and remediation with Claude, with skills for threat modeling, scanning, triage, and patching. audit - Eight-stage discovery agent built on the Claude Code SDK, combining many narrow agents, deliberate disagreement between them, and an explicit reachability gate. Capital One VulnHunter - Agentic security tool applying proactive, attacker-first analysis directly to source code. Clearwing - Autonomous source-code hunter that ranks files, fans out specialist agents, and treats sanitizer crashes as ground truth, with a separate network-pentest mode. Cloudflare Security Audit - Six-phase audit skill: parallel hunting agents attack the codebase from different angles, separate agents try to disprove each finding, and fresh agents verify the schema-validated findings.json against source. SKILL.md. Google Mantis - Modular, s