Ten years ago I published a free Android application security series at manifestsecurity(dot) com/android-application-security. At the time, Android security had almost no free material to learn from — web security had plenty. That gap is why I wrote it. It still gets traffic today, and people still message me saying it's how they learned Android pentesting. AI security has that same gap right now. So I'm rebuilding it — this time for AI. genaisecuritylab.com/learn is live. It teaches LLM security the way you'd actually test it. Short concept material, then live labs in your browser where you run the full loop: Attack → Defend → Verify. You exploit a real target, implement the fix, and verify the fix holds. Every topic has an offensive and a defensive track. It's a live system you break with your own hands — not a module you click through. Two are live today: AI Security Foundation, and Prompt Injection start to finish — direct, jailbreaks, encoding, smuggling, indirect, tool/agent-mediated, and the defense for each. Over the next 12 weeks I'll publish the rest free, one part a week, for pentesters and AppSec engineers who already know web and need to add AI to their scope: • System prompt and secret extraction • RAG data leakage and cross-tenant bleed • Agent and MCP tool abuse, excessive agency • Improper output handling → second-order injection The point: applications are shipping with LLM components now, and clients are starting to ask for AI testing. This gets you ready for that. Every part maps to the OWASP LLM Top 10 (2026), the Agentic Top 10, and the MCP Top 10 — and every part ends in a live hosted lab you attack right in the browser. No setup, no API keys, no Docker. Attack it, fix it, prove the fix holds. I'm picking 100 people as the founding cohort — early access to each part before it goes public, a private channel with me, and your feedback directly shaping the curriculum. If you want in, say so in the comments. I'll reply to every one and send you the link. #AISecurity #AppSec #LLMSecurity

AI agents now cover most of the deterministic vulnerabilities we spent the last 15 years mastering 😄 It's made me think about how our role as pentesters and security engineers will evolve — not because those skills are gone, but because AI/LLM, Agentic and MCP security are quietly moving from "specialty" to essential skill. I’ve shared a few thoughts here: genaisecuritylab.com/blog/no… Would love to hear your thoughts on this! 🙌

Nobody got good at web security by reading about SQL injection. You got good by breaking things, then fixing them. AI security is becoming that same baseline skill — the one every pentester, AppSec engineer, and developer shipping AI features is about to be expected to have. And almost all the training for it is passive: a slide deck and a multiple-choice quiz. So we built the opposite. GenAI Security Lab: 200+ live, deliberately vulnerable AI targets running on real models. LLM chat apps, MCP servers, RAG pipelines, tool-using agents. One attack technique per target. Nobody reads a wall of text, so we didn't write one. Each OWASP topic is a guided path, not a PDF — a few-minute concept video, a diagram of exactly where the trust boundary breaks, the real incident behind it, and predict-before-reveal checkpoints that make you commit before you ever touch the target. Then you run the loop: Attack → Defend → Verify. Exploit it for real, implement the fix, verify it holds — across two tracks per topic, offensive and defensive. It's a live system you break with your own hands, then close the hole you found. Not a module you click through. Why it's built this way: I've spent years as a top bug bounty hunter and a decade in security consulting. The only thing that ever made me better was breaking real systems. This is the training I wanted when I started on AI. It's live today. Community labs are free — no credit card: genaisecuritylab.com Running a team? Per-seat plans, one methodology across every engineer, and completion records that mean something — because your people earned them on live targets, not a webinar sign-in.

Ever since the AI/LLM wave hit, I've been keeping a scrappy little personal list — the payloads and techniques I actually reach for when testing AI apps. My own private cheat sheet, basically. And lately, so many of us keep hearing the same question from clients: "Can you security-test the AI part too?" Honestly? Most folks I've talked to didn't have a solid methodology for it yet. No judgment — this space is moving at light speed, and we've all been figuring it out as we go. So today I'm genuinely excited to finally share mine: the AI Security Testing Cheat Sheet, part of the @genaiseclab project. Here's what's inside: 🔍 150+ practical techniques across 20 sections — all mapped to the OWASP LLM Top 10 2026 💉 Prompt injection, indirect & multimodal injection, sensitive data disclosure, tool and agent abuse, MCP attacks 📝 Real example payloads for every technique 📋 A tracker you fill in as you test, plus findings export and reporting templates And the best part — it's truly free. No signup, no credit card, no gate. Just grab it and go. ❤️ This is a living project, too. If there's a technique you think I've missed, I'd genuinely love to hear it — drop a comment or DM me and I'll fold it in. This thing gets better when we build it together. 👉 genaisecuritylab.com/cheatsh… If it saves you even a few hours on your next assessment, that honestly makes my week. And feedback — good or bad is welcome, so tell me what you think! 🙏

We've added a huge new topic, on XXE (XML external entity) injection. Lots of new content and 9 new labs! portswigger.net/web-security…

@appsecwiki has one of the most comprehensive and high quality appsec resources I have seen. I am using it now to learn AppSec appsecwiki.com/

Added a DevSecOps section in @appsecwiki with some intial links. Will continue to add more resources as i learn more about it. Please add links/resources you are aware of. Thanks! appsecwiki.com/#/devsecops

GitHub Desktop RCE (OSX) Bug Bounty writeup: pwning.re/2018/12/04/github-… Thank you @GitHubSecurity for the bounty!

Story of my two (but actually three) RCEs in SharePoint in 2018: soroush.secproject.com/blog/… - it all began with a simple question in Jan. 2018: "have you worked with ysoserial .net?" what a year! Glad blackhat.com/docs/us-17/thur… is in Top 10 Web Hacking Techniques of 2017 @pwntester

New write up - "Reading ASP secrets for $17,000" - the really fun process of exploiting local file disclosure 🧐 samcurry.net/reading-asp-sec…

There's a common misconception that 'X-Frame-Options: allow-from hxxp://example.com/' prevents framing. In fact, this isn't secure because Chrome doesn't support allow-from and never will: bugs.chromium.org/p/chromium… So you can stop reporting Burp's XFO check as a false positive :)

Hackers, minor cool insight that I gained some time ago and found a vulnerability with: when you're looking at an asset that may use a microservices architecture, look for IDOR vulnerabilities using path traversal. E.g. https://example/?id=1/../2. See thread. #TogetherWeHitHarder

Remote Code Execution with EL injection #bugbounty #RCE betterhacker.com/2018/12/rce…

This is very interesting!

A small gift from S2anta: @breenmachine showed how to abuse JasperReports for RCE (foxglovesecurity.com/2016/10…) - now here's a single .JRXML file to achieve the same thing if no .JAR's are allowed: gist.github.com/v-p-b/dd95c7…

We just shipped our first newsletter. You can subscribe to newsletter at appsecwiki.com/#/?id=newslet… if you have not already. Here is the link to this week newsletter: mailchi.mp/7d632ba1dc74/apps… Thanks!

My latest #bugbounty writeup: A $2,500 IDOR in New Relic that allowed me to run NRQL queries and retrieve data from any New Relic account. You can read it here: jonbottarini.com/2018/10/09/… Let me know what you think! #TogetherWeHitHarder #HackerOne

An interesting #Google vulnerability that got me 3133.7 reward. sec-down.com/wordpress/?p=80…

My new blog post. GoogleMeetRoulette: Joining random #Google meetings. Enjoy! martinvigo.com/googlemeetrou…

Hello Twitter! #myfirstTweet