llms.txt
# Hacktron AI
> Hacktron is an AI-native security platform for code reviews and penetration tests. It helps teams find and fix exploitable vulnerabilities in their applications to defend against AI-powered threats.
Use this file as a concise map of the public Hacktron website. For expanded context, use /llms-full.txt.
## Security coverage
- Code security · Review: Secure every change before it ships. Hacktron catches and validates vulnerabilities in pull requests, giving developers the confidence to move fast without drowning in noise.
- Product security · Whitebox Pentest: Uncover real security issues in production. Hacktron combines deep source-code context with active testing to uncover how weaknesses across your services could lead to a real breach.
- Organization security · Continuous red teaming: Simulate a persistent adversary.
## Pricing
- PR Review: Pro Plan from $40 / developer / mo. For small teams securing their development workflow. 50 PRs (unlimited scans per PR) per developer, $1 per additional PR; Auto-triage & autofix to verify findings and prepare tested fixes; Self-improving threat models based on triage feedback; GitHub, GitLab, Bitbucket, and Azure DevOps integrations. Start 14-Day Free Trial. No credit card required. Free for Open Source. Enterprise: Custom pricing.
- Whitebox: Basic Application from $100; Mature Application from $2,000; Enterprise: Custom pricing. All pentests receive the same assessment depth and quality. Get an instant quote based on codebase size and number of repositories.
- [Continuous red teaming](https://www.hacktron.ai/#pricing): Custom pricing. Simulate a persistent adversary. Ongoing adversarial testing across your attack surface; Validated attack paths with clear guidance for remediation; Custom scope tailored to your organization. [Contact Us](https://www.hacktron.ai/calendar).
## Featured research
- [HEIF Heist](https://heif-heist.com/): One image parser to pwn them all. Research from Hacktron.
## In the news
- [News and press](https://www.hacktron.ai/news): Press coverage of Hacktron’s research and company news.
- [Hackers who broke into OpenAI warn the AI industry has a security problem](https://www.washingtonpost.com/technology/2026/09/20/breach-chatgpt-maker-openai-highlights-risks-ai-getting-hacked/): The Washington Post · 2026-09-20. More powerful AI magnifies cyberattack risks.
- [Researchers used Claude to hack OpenAI](https://arstechnica.com/ai/2026/09/researchers-used-claude-to-hack-openai/): Financial Times · via Ars Technica · 2026-09-18. Researchers used Claude to reach an OpenAI employee account and sensitive GitHub data.
- [Hackers Used Anthropic’s Claude to Break Into OpenAI](https://www.wsj.com/tech/ai/hackers-used-anthropics-claude-to-break-into-openai-b40ba883): The Wall Street Journal · 2026-09-17. A bug-hunting independent security research team accessed OpenAI’s internal code system, exposing growing risks in automated cyber threats
- [Active Exploitation Attempts Target WSO2 API Manager JWT Bypass](https://thehackernews.com/2026/09/active-exploitation-attempts-target.html): The Hacker News · 2026-09-16. Attackers are targeting a critical WSO2 flaw reported by Hacktron that can put administrative accounts at risk.
- [Attackers pummel critical WordPress vuln to create all sorts of mischief](https://www.theregister.com/security/2026/07/20/attackers-pummel-critical-wordpress-vuln-to-create-all-sorts-of-mischief/5275265): The Register · 2026-07-20. Plus dozens of PoCs in the public domain
- [Two new high severity WordPress vulnerabilities, patch immediately!](https://www.helpnetsecurity.com/2026/07/18/wordpress-vulnerabilities-wp2shell-cve-2026-60137-cve-2026-60137/): Help Net Security · 2026-07-18. The 7.0.2 WordPress security release addresses one critical and one high severity security issue.
- [GPT-5.6 Sol Ultra Builds Full Chrome Exploit Chain From Security Patches](https://cybersecuritynews.com/gpt-5-6-sol-chrome-exploit-chain/): Cyber Security News · 2026-07-15. In Hacktron’s comparison of three AI models, only Sol Ultra completed the Chrome challenge, costing about $1,597.
- [Major GNU software repository Savannah fixes two-year flaw](https://cybernews.com/security/gnu-savannah-patches-two-year-security-flaw/): Cybernews · 2026-06. GNU Savannah, a major platform for developing and distributing free software, said it had patched exploitable flaws that left it vulnerable for roughly 2 years.
- [Hacktron Plans to Build AI Platform to Test Code for Vulnerabilities](https://devops.com/hacktron-plans-to-build-ai-platform-to-test-code-for-vulnerabilities/): DevOps.com · 2026-05-13. After raising $2.9 million, Hacktron is building a platform to test code changes and separate exploitable vulnerabilities from false positives.
- [Claude Opus wrote a Chrome exploit for $2,283](https://www.theregister.com/security/2026/04/17/claude-opus-wrote-a-chrome-exploit-for-2283/5219906): The Register · 2026-04-17. Pause your Mythos panic because mainstream models anyone can use already pick holes in popular software
- [Cloudflare’s Next.js alternative faces critical security flaws](https://cybernews.com/security/hackers-find-critical-flaws-in-cloudflares-nextjs-alternative/): Cybernews · 2026-03. Cloudflare’s AI-built Next.js alternative launched with critical security flaws, intensifying its rivalry with Vercel.
- [BeyondTrust fixes critical RCE flaw in remote access tools](https://www.csoonline.com/article/4130415/beyondtrust-fixes-critical-rce-flaw-in-remote-access-tools.html): CSO Online · 2026-02-10. Organizations running BeyondTrust’s self-hosted remote access software are urged to patch a vulnerability rated 9.9 out of 10.
- [BeyondTrust warns of critical RCE flaw in remote support software](https://www.bleepingcomputer.com/news/security/beyondtrust-warns-of-critical-rce-flaw-in-remote-support-software/): BleepingComputer · 2026-02-09. BeyondTrust patched its cloud services and urged on-premises customers to update after Hacktron discovered a critical vulnerability.
- [BeyondTrust Fixes Critical Pre-Auth RCE Vulnerability in Remote Support and PRA](https://thehackernews.com/2026/02/beyondtrust-fixes-critical-pre-auth-rce.html): The Hacker News · 2026-02-09. A critical vulnerability in BeyondTrust’s remote access products could allow unauthenticated attacks without user interaction.
## Product
- [Hacktron AI](https://www.hacktron.ai/): AI-Native Cybersecurity Platform. Security for the age of AI-powered threats.
- [AI Code Review & SAST for Pull and Merge Requests](https://www.hacktron.ai/pr-review): AI security reviewer for pull and merge requests with codebase context, inline findings in GitHub and GitLab, project-specific learning, automatic resolution, and customer evidence from Krisp, Zellify, Rocket.Chat, Novu, Mobbin, hackajob, and Nopan.
- [AI SAST: Exploit-Aware Static Analysis](https://www.hacktron.ai/solutions/ai-sast): AI SAST that reasons about code in context and validates each finding with a proof-of-concept exploit, reducing false positives and catching business-logic flaws.
- [Security Workflow Automations](https://www.hacktron.ai/automations): Connect security triggers to actions and notifications. Remediate can automatically verify and remediate every matching finding, prepare a review-ready change for real issues, and record false-positive or no-change decisions. Each organization receives a one-time allocation of 5000 free credits.
- [AI White-box Penetration Testing as a Service](https://www.hacktron.ai/pentests): Hacktron Whitebox pentests with code-aware analysis, validated findings, researcher review, a Yoto customer testimonial, and audit-ready reports for SOC 2 and ISO 27001.
- [Offensive Security Services](https://www.hacktron.ai/services): Expert-led offensive security engagements combining elite security researchers with frontier models: external and internal AI-assisted red teaming, cloud and firmware assessments, purple team exercises, advisory, and independent review, with live reporting, a final report, and fix verification.
- [Dependency Scanner](https://www.hacktron.ai/package): Scan package-lock.json, pnpm-lock.yaml, yarn.lock, uv.lock, and poetry.lock files against 21,000+ known malware advisories instantly.
- [Open Source Program](https://www.hacktron.ai/open-source): Free Hacktron PR and MR security reviews for qualifying open source projects.
- [Case Studies](https://www.hacktron.ai/customer-stories): Customer stories from teams using Hacktron for security code reviews.
- [Security Advisories](https://www.hacktron.ai/advisories): Coordinated disclosures and advisories for vulnerabilities discovered or reported by Hacktron researchers, with Supabase customer evidence for Hacktron security research.
- [Security Changelog](https://www.hacktron.ai/security-changelog): Security-only changelog for framework vulnerability fixes, affected versions, fixed versions, CVEs, workarounds, and upstream advisories.
- [Blog](https://www.hacktron.ai/blog): Security research, exploit writeups, product updates, and offensive security analysis from Hacktron.
## Research
- [Hacking OpenAI](https://www.hacktron.ai/blog/hacking-openai): 2026-09-13. A heap overflow and SSO misconfiguration to compromise OpenAI internal repositories
- [Here’s How an OpenAI Model Went Rogue and Hacked Hugging Face](https://www.hacktron.ai/blog/here-is-how-openai-model-hacked-huggingface): 2026-07-23. OpenAI and Hugging Face probably won’t tell us exactly how the whole incident unfolded. But using publicly available data, we can reconstruct what likely happened.
- [Could Modern Code Review Have Prevented wp2shell?](https://www.hacktron.ai/blog/wp2shell): 2026-07-19. We recreated the WordPress pull requests behind CVE-2026-63030 and CVE-2026-60137 to test whether today's code reviewers and SAST tools would catch both vulnerabilities.
- [Breaking Into PostHog Prod Database](https://www.hacktron.ai/blog/posthog-rce): 2026-07-15. Escalating a Hacktron finding into a PostHog production RCE using Claude, and challenging open-weight models to write the same V8 exploit.
- [Watching GPT-5.6 Sol Ultra Write a Chrome Exploit: Exploit Development as We Know It Is Dead](https://www.hacktron.ai/blog/watching-gpt-55-sol-ultra-write-a-chrome-exploit-exploit-development-as-we-know-it-is-over): 2026-07-14. We benchmarked the latest frontier models, GPT-5.6 Sol Medium, Sol Ultra, and Grok 4.5, on their exploit-development capabilities. After processing 2.096 billion tokens, Sol Ultra was the only model to produce a complete exploit chain.
- [GLM and DeepSeek Are Catching Frontier Models at Finding Vulnerabilities](https://www.hacktron.ai/blog/open-weight-models-vs-frontier-models): 2026-07-08. We benchmarked GLM, DeepSeek, Kimi, and MiniMax against GPT, Claude, Gemini, and Opus on 15 real vulnerabilities patched in Fider, an open-source Go and React app. Frontier models still lead, but open-weight models are closing the gap fast.
- [Metabase Cloud: The winner takes it all](https://www.hacktron.ai/blog/metabase-cloud): 2026-06-25. We could have pwned every Metabase Cloud tenant by chaining an H2 INIT sanitizer bypass into RCE, then cloud misconfigurations into a full multi-tenant cluster compromise.
- [The Attack Surface Is Everyone Now](https://www.hacktron.ai/blog/the-attack-surface-is-everyone-now): 2026-06-09. Why AI is broadening the attack surface across OSS, new SaaS, and fast-shipping teams, and how to position yourself with an assume-breach mindset.
- [Hacktron's $350 Pentest vs XBOW and Aikido at $4,000](https://www.hacktron.ai/blog/hacktron-vs-xbow-and-aikido): 2026-06-05. We ran the same scan Doyensec used to test XBOW and Aikido, for a tenth of the price. Here's how our $350 AI pentest compared.
- [When Your VPN Opens Your Private Network to the Public](https://www.hacktron.ai/blog/cve-2026-0265-panos-globalprotect-cas-auth-bypass): 2026-05-20. How AI-assisted reverse engineering of stripped PAN-OS binaries led to finding a JWT algorithm confusion vulnerability in GlobalProtect's Cloud Authentication Service, enabling full VPN auth bypass with just a username.
- [RCE in VSCode Copilot Chat](https://www.hacktron.ai/blog/rce-in-vscode-copilot): 2026-05-13. Copilot agent mode is vulnerable to a prompt injection attack. If a repository maintainer clicks 'code with agent mode' on an issue, it will open a new codespace and copilot will automatically run the issue's description.
- [Hacktron Review for Open Source](https://www.hacktron.ai/blog/hacktron-review-for-open-source): 2026-05-08. We are opening up Hacktron Review for Open Source, giving qualifying maintainers free PR security reviews with inline findings, auto-resolution, and project-specific learning.
## Customer Stories
- [How Hacktron brings context-aware security review to every change in Nopan’s payments infrastructure](https://www.hacktron.ai/customer-stories/nopan): As code volume and AI-assisted development grow, Nopan uses Hacktron to deepen its security review without slowing continuous delivery.
- [How Hacktron brings codebase-wide security context to every hackajob pull request](https://www.hacktron.ai/customer-stories/hackajob): hackajob runs every pull request through Hacktron Review for codebase-wide security context, catching a cross-customer authorization gap before merge.
- [How Mobbin achieves near-immediate security triage with Hacktron](https://www.hacktron.ai/customer-stories/mobbin): Mobbin uses Hacktron Review to bring full-codebase security review into every pull request, with a 32-minute median time to triage.
- [How Hacktron gives Novu's security team confidence, not more process](https://www.hacktron.ai/customer-stories/novu): How Novu catches cross-file vulnerabilities like NoSQL injection in a codebase 400+ contributors touch, with 83% of triaged findings actionable.
- [How Hacktron provides 24/7 security for Rocket.Chat](https://www.hacktron.ai/customer-stories/rocketchat): How Rocket.Chat found and fixed a critical Apple OAuth account takeover (CVE-2026-55666) within days of adding Hacktron to every pull request.
- [Why Krisp chose Hacktron for security code reviews](https://www.hacktron.ai/customer-stories/krisp): How Krisp's security team gets high-signal vulnerability detection on every pull request with Hacktron, without slowing down engineering.
## Security Review Guides
- [Best automated security testing tools for pull requests in 2026](https://www.hacktron.ai/blog/best-automated-security-testing): Compare automated security testing tools that integrate with pull requests for inline findings, exploitability validation, and developer-ready fixes.
- [Hacktron vs Snyk: Which Catches More in a Pull Request in 2026](https://www.hacktron.ai/blog/hacktron-vs-snyk-pr-review): Compare Hacktron and Snyk for pull request security review, including dependency scanning, SAST coverage, exploitability reasoning, false positives, and workflow fit.
- [AI code review for security: what actually matters before merge](https://www.hacktron.ai/blog/ai-code-review-for-security): How to evaluate AI code review for security, why general review comments are not enough, and how PR-native security review catches risky changes earlier.
- [Securing AI-generated code before it merges](https://www.hacktron.ai/blog/ai-generated-code-security-risks): A practical guide to AI-generated code security risks, including auth mistakes, prompt injection paths, unsafe dependencies, and PR review guardrails.
- [AI SAST: code analysis that reviews exploitability, not just patterns](https://www.hacktron.ai/blog/ai-sast): A practical guide to AI SAST, traditional SAST blind spots, and how Hacktron reviews pull requests for exploitable security issues.
- [AI SAST vs traditional SAST: what changes in security review](https://www.hacktron.ai/blog/ai-sast-vs-traditional-sast): Compare AI SAST and traditional SAST across rule coverage, exploitability reasoning, business logic bugs, pull request review, and remediation workflow.
- [AI security review for modern software teams](https://www.hacktron.ai/blog/ai-security-review): A practical explanation of AI security review, where it fits in AppSec, and why exploitability-focused pull request review is different from scanner triage.
- [Top Aikido alternatives for developer security in 2026](https://www.hacktron.ai/blog/aikido-alternative): A practical list of Aikido alternatives for teams comparing PR security review, AI SAST, broad AppSec coverage, SCA, and developer-friendly workflows.
- [Top 10 AI-powered SAST tools for AppSec teams in 2026](https://www.hacktron.ai/blog/best-ai-sast-tools): Compare AI-powered SAST tools for PR security review, semantic analysis, autofix, exploitability triage, and traditional scanner coverage.
- [Best PR security review tools for engineering teams in 2026](https://www.hacktron.ai/blog/best-pr-security-review-tools): Compare PR security review tools for inline findings, AI code review, SAST checks, exploitability reasoning, and developer-ready fixes.
- [Top CodeRabbit alternatives for security-focused PR review in 2026](https://www.hacktron.ai/blog/coderabbit-alternative): A practical list of CodeRabbit alternatives for teams comparing AI code review, PR security review, full-codebase context, and exploitable findings.
- [Top Greptile alternatives for AI security review in 2026](https://www.hacktron.ai/blog/greptile-alternative): A list of Greptile alternatives for teams comparing repository-aware AI code review, PR security review, AI SAST, and exploitability-focused findings.
- [IaC security review for pull requests](https://www.hacktron.ai/blog/iac-security-code-review): How to review Terraform, GitHub Actions, cloud permissions, and infrastructure-as-code changes for security before they reach production.
- [PR security review: catching vulnerabilities before merge](https://www.hacktron.ai/blog/pr-review-for-security): Why pull requests are the best place to review security-sensitive code, and how Hacktron turns PR review into a practical AppSec workflow.
- [SAST vs DAST vs PR security review](https://www.hacktron.ai/blog/sast-vs-dast-vs-pr-security-review): Compare SAST, DAST, and PR security review, including where each fits, what each misses, and how to catch exploitable issues before merge.
- [How to secure AI coding agents before they ship vulnerable code](https://www.hacktron.ai/blog/secure-ai-coding-agents): A practical guide to securing AI coding agents with dependency controls, secrets checks, PR security review, prompt injection review, and project rules.
- [Top Semgrep alternatives for AppSec teams in 2026](https://www.hacktron.ai/blog/semgrep-alternative): A list of Semgrep alternatives for teams comparing AI SAST, PR security review, CodeQL, enterprise SAST, and tools that go beyond pattern matching.
- [Top Snyk alternatives for PR security review in 2026](https://www.hacktron.ai/blog/snyk-alternative): A practical list of Snyk alternatives for teams that need higher-signal PR security review, AI SAST, exploitability context, and developer-ready fixes.
## Advisories
- [HTAI-028: GitHub - Concurrent upload race leads to GitHub Enterprise Server RCE](https://www.hacktron.ai/advisories): high RCE; CVE-2026-19118. An authenticated user with repository write access can exploit a race between concurrent upload requests to execute code on GitHub Enterprise Server.
- [HTAI-027: libheif - Duplicate alpha planes trigger a libheif heap overflow](https://www.hacktron.ai/advisories): critical RCE; CVE-2026-84383. A crafted HEIF image with nested derived images and duplicate alpha planes can overflow a heap buffer during scaling, allowing remote code execution in applications processing the image.
- [HTAI-015: WSO2 - JWT algorithm mismatch allows WSO2 authentication bypass](https://www.hacktron.ai/advisories): critical Auth Bypass; CVE-2026-5430. WSO2 JWT authentication accepts unsupported signing algorithms, allowing crafted
