Penetration and security testing tools for coding agents
Agents that probe apps and code the way an attacker would and report vulnerabilities. Of the 964 tools on our writing code page, 12 fit this narrower job. By pricing: 10 open source, 2 pricing on the maker's site. The most-starred open repos here are CyberStrike (3,305 stars), Redamon (3,246 stars), Mantis (2,675 stars). Most come from the security & governance (5), MCP servers (5), evals & observability (1) categories.
Updated
CyberStrike
Terminal agent for authorized penetration testing that runs recon, vulnerability discovery and reporting with specialized security agents on your own LLM.
Added
Redamon
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what.
Added
Mantis
Google's toolkit for AI coding agents to autonomously find, reproduce and patch software vulnerabilities in isolated environments.
Added
Rogue
Agent evaluator and red-team tool that probes your agent with test conversations and attacks and reports pass or fail against your policies.
Added
Aletheore
Aletheore audits code repositories and backs every finding with evidence. Its deterministic scanner looks for leaked secrets, vulnerable dependencies and dead code, it can watch live endpoints and draw architecture maps, and it reviews pull requests automatically through a GitHub Action. A built-in MCP server lets coding agents run the same audits.
Added
0.security
0 is an open, self-improving AI operating system for offensive security work. Its agents investigate code and binaries for vulnerabilities, test defenses, verify findings with working proofs and help fix the issues, and the team behind it publishes the advisories it has found in real open-source projects.
Added
Mira
Mira is an open-source agent project that helps builders handle AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs.
Added
GitHits
GitHits is an MCP server agents call to search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Added
Feldspar free repository security scan
Feldspar free repository security scan is an MCP server that gives agents a way to handle deterministic security scan of public git repos: OSV.dev vulnerable deps, secrets, config.
Added
Octane
Agentic security analysis that finds exploitable vulnerabilities in mission-critical code, including DeFi smart contracts.
Added
Ostorlab
Query and act on your Ostorlab scans, vulnerabilities, tickets and assets.
Added
Sekura
Sekura is an MCP server agents call to scan a GitHub repository for vulnerabilities, with proof for every finding.
Added
GitHub repos (10)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| 3,305 | โ | 2026-10-14 | |
| 3,246 | โ | 2026-10-28 | |
| 2,675 | Apache 2.0 | 2026-10-25 | |
| 1,072 | โ | 2026-05-04 | |
| 659 | โ | 2026-10-30 | |
| 558 | โ | 2026-10-28 | |
| 396 | โ | โ | |
| 128 | โ | โ | |
| 1 | โ | โ | |
| 0 | โ | โ |
10 repos. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for writing code focused on penetration and security testing?
We list 12. The first three by GitHub stars and featured status are CyberStrike: Terminal agent for authorized penetration testing that runs recon, vulnerability discovery and reporting with specialized security agents on your own LLM.; Redamon: Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what.; Mantis: Google's toolkit for AI coding agents to autonomously find, reproduce and patch software vulnerabilities in isolated environments.
Are there free or open-source options?
Yes: 10 open source, 2 pricing on the maker's site. Pricing is as each maker states it.
More from writing code
Tools are grouped by what each says it does. Missing one? Submit it free.