Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Compound Security An open-source skill that helps your coding agent find vulnerabilities, patch them, and test that your app still works. Here’s how you use it: → Help: figure out where to start → Brainstorm: pick what matters → Patch: plan, fix, and verify → LFG: take it... show more

imran

18,998 subscribers

11,539 views • 5 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

53 Comments

imran5 days ago

if you want to give it a shot ->

GREG ISENBERG5 days ago

imran is cooking

imran5 days ago

im just tryna get like you big bro

Isa3 days ago

Trying it out!

imran3 days ago

thank you! lmk what you think !

Yousef5 days ago

trying this out rn

imran5 days ago

please let me know what i can improve

hamza mostafa5 days ago

let him cook!

dale5 days ago

Very cool

Ahmed Reza5 days ago

Agent - Market fit right here!

Robleh5 days ago

giving the people what they need!

imran5 days ago

heck yea, your security should compound

du5 days ago

He's Himran

imran4 days ago

i’m tryna get like du

Nader Khalil🍊5 days ago

Excited to try this

Imaad Malik4 days ago

yoo trying this shi rn

imran4 days ago

lmk what you think

Dominik5 days ago

great!

jia5 days ago

let’s go imran👏👏

imran5 days ago

you are my inspiration fr

rowan5 days ago

Is it deepseek proof though?

imran5 days ago

summon the chinese one

Aly Moursy5 days ago

Trying

imran5 days ago

hell yea!

dale5 days ago

Gonna try this out

imran5 days ago

lmk what you think!

Peyton Casper5 days ago

trying this tonight, lfg

imran5 days ago

goated

Howard Zhong5 days ago

let’s goo imran 🔥

Bilal5 days ago

🔥🔥

imran5 days ago

we're cooking

Emiliano Bonassi5 days ago

oh damn, finally someone did this! pretty cool, gonna try it asap with our obliterated models

imran4 days ago

lmk how it goes!

Emiliano Bonassi4 days ago

starting with autonomous swarms here they survive only if they find bugs and get payed

Alex5 days ago

Oh hell yeah, can’t wait to try it

Kyle5 days ago

Patch then test is what I want. Does it rerun the app checks after every fix or only at the end ?

imran5 days ago

you can steer it to

Safwan5 days ago

installed!

Nour Zahzah5 days ago

Nice

imran5 days ago

give it a whirl and lmk what you think

Jibraan4 days ago

big if true

Ahmed Karrar5 days ago

lets goooooo

Moummar5 days ago

on a roll

imran5 days ago

just tryna get like you

mspaintperry5 days ago

This is tooo good!!!

Ahmad Bukhari | AI GTM Engineer5 days ago

Nice that it starts with Help. First place I'd send it: anywhere one customer can see another customer's data.

imran5 days ago

good idea!

mal5 days ago

LESSGOOO

AMIT KALRA5 days ago

@YGnacko I couldn’t pay attention to what ur saying ur too handsome

John Rood5 days ago

the audit has to run in a session that didn't write the code. same-session review inherits every assumption that caused the bug, so the agent ends up defending the design instead of attacking it. give it the repo in a fresh context with no history and the findings get a lot less polite.

imran5 days ago

well you could always just give it the trace lol

John K5 days ago

The tricky part with agentic patching is usually generating the reproduction test first. Does this write an exploit test to verify the fix, or just rely on existing suites?

timo4 days ago

solid skill

Related Videos

We're introducing Codex Security. An application security agent that helps you secure your codebase by finding vulnerabilities, validating them, and proposing fixes you can review and patch. Now, teams can focus on the vulnerabilities that matter and ship code faster.

We're introducing Codex Security. An application security agent that helps you secure your codebase by finding vulnerabilities, validating them, and proposing fixes you can review and patch. Now, teams can focus on the vulnerabilities that matter and ship code faster.

OpenAI Developers

1,721,117 views • 8 months ago

This is such a powerful AI coding workflow. You can now use Cursor or Windsurf for coding, and let CodeRabbit’s AI agent refactor messy code, help you debug, and find security vulnerabilities. Here’s how:

This is such a powerful AI coding workflow. You can now use Cursor or Windsurf for coding, and let CodeRabbit’s AI agent refactor messy code, help you debug, and find security vulnerabilities. Here’s how:

Alvaro Cintas

79,897 views • 1 year ago

Introducing EvoSkill V1, an open-source toolkit that takes a benchmark and a coding agent, and evolves it into a state-of-the-art specialist in minutes. Here’s all you need to start evolving, starting with your Claude Code ↓

Introducing EvoSkill V1, an open-source toolkit that takes a benchmark and a coding agent, and evolves it into a state-of-the-art specialist in minutes. Here’s all you need to start evolving, starting with your Claude Code ↓

Sentient

30,234 views • 6 months ago

Composal (YC F26) sends a swarm of agents through your product to test it the way real users do. Your coding agents build it; ours break it, record the evidence, and hand your agent what it needs to fix and re-verify.

Composal (YC F26) sends a swarm of agents through your product to test it the way real users do. Your coding agents build it; ours break it, record the evidence, and hand your agent what it needs to fix and re-verify.

Pandelis

132,108 views • 12 days ago

OpenAI turned its most capable cyber models against their own infrastructure to continuously attack their systems. In the age of AI-powered attacks, defense factories that find vulnerabilities, remediate them, and verify the patch autonomously are the only way to stay secure. We've spent months building this with major healthcare systems and cloud providers. Today, we’re making it available to everyone. > Find: Continuously probes your systems to identify vulnerabilities > Fix: Writes the fixes and opens PRs for review > Verify: Retests every patch until the vulnerability is gone Find. Fix. Verify. Repeat.

OpenAI turned its most capable cyber models against their own infrastructure to continuously attack their systems. In the age of AI-powered attacks, defense factories that find vulnerabilities, remediate them, and verify the patch autonomously are the only way to stay secure. We've spent months building this with major healthcare systems and cloud providers. Today, we’re making it available to everyone. > Find: Continuously probes your systems to identify vulnerabilities > Fix: Writes the fixes and opens PRs for review > Verify: Retests every patch until the vulnerability is gone Find. Fix. Verify. Repeat.

Antigen

103,946 views • 27 days ago

Today we're introducing Genii. An open source personal assistant that lives in your messages. You just text it. It remembers what matters to you, connects to your inbox and calendar, and texts you first when something needs you. Intelligence that meets you where you are. Get yours:

Today we're introducing Genii. An open source personal assistant that lives in your messages. You just text it. It remembers what matters to you, connects to your inbox and calendar, and texts you first when something needs you. Intelligence that meets you where you are. Get yours:

Intelligent Internet

24,811 views • 3 months ago

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Dria

44,203 views • 5 months ago

OpenAI just released Codex Security, an AI agent that scans software projects to fix vulnerabilities while ignoring harmless bugs. Testing on 1.2mn commits found 792 critical flaws and dropped false alarms by 50%. Here is how the Codex Security agent works Initially, it scans your software project to learn how all the different pieces of code connect. It uses that knowledge to build a threat model, which acts as a custom map showing exactly where your software might be exposed to hackers. The agent then hunts for potential security holes based on that specific map. When it spots a possible flaw, it does not just send you a random alert. Instead, it creates a completely safe and isolated copy of your system known as a sandbox. The agent then actively tries to break into that sandboxed copy to prove if the security weakness is a real danger. If the agent successfully exploits its own test environment, it knows the bug is a genuine threat and not a false alarm. After confirming the danger, the agent writes a custom software patch to fix the broken code. It then tests that new patch to guarantee the fix does not accidentally break any other features in your software.

OpenAI just released Codex Security, an AI agent that scans software projects to fix vulnerabilities while ignoring harmless bugs. Testing on 1.2mn commits found 792 critical flaws and dropped false alarms by 50%. Here is how the Codex Security agent works Initially, it scans your software project to learn how all the different pieces of code connect. It uses that knowledge to build a threat model, which acts as a custom map showing exactly where your software might be exposed to hackers. The agent then hunts for potential security holes based on that specific map. When it spots a possible flaw, it does not just send you a random alert. Instead, it creates a completely safe and isolated copy of your system known as a sandbox. The agent then actively tries to break into that sandboxed copy to prove if the security weakness is a real danger. If the agent successfully exploits its own test environment, it knows the bug is a genuine threat and not a false alarm. After confirming the danger, the agent writes a custom software patch to fix the broken code. It then tests that new patch to guarantee the fix does not accidentally break any other features in your software.

Rohan Paul

13,208 views • 8 months ago

Find up and coming open source projects before anyone else. Introducing Grepository, a new way to find which repos are trending, and how to use them in your workflow.

Find up and coming open source projects before anyone else. Introducing Grepository, a new way to find which repos are trending, and how to use them in your workflow.

Greptile

22,479 views • 9 months ago

Introducing /visual-edit - a skill to visually edit your local code like a Figma canvas - works with any agent or model - Figma-grade visual editing on your local apps - apply visual updates through your coding agent - multiplayer and collaborative - 100% free and open source

Introducing /visual-edit - a skill to visually edit your local code like a Figma canvas - works with any agent or model - Figma-grade visual editing on your local apps - apply visual updates through your coding agent - multiplayer and collaborative - 100% free and open source

Steve (Builder.io)

49,460 views • 1 month ago

Antigravity’s browser sub-agent can "look" at your app, scroll through it, and click to verify that everything works before you deploy. It’s built-in safety using screenshots and recordings. See the browser agent verify a live build →

Antigravity’s browser sub-agent can "look" at your app, scroll through it, and click to verify that everything works before you deploy. It’s built-in safety using screenshots and recordings. See the browser agent verify a live build →

Google Cloud Tech

28,286 views • 8 months ago

Introducing patch: build and play games. - Every game dev tool in one CLI and MCP - 50,000+ open-source assets - Remix any game on patch, or mod the ones on your PC - Ship it to everyone on patch, opensource :) We're opening it to everyone today:

Introducing patch: build and play games. - Every game dev tool in one CLI and MCP - 50,000+ open-source assets - Remix any game on patch, or mod the ones on your PC - Ship it to everyone on patch, opensource :) We're opening it to everyone today:

Rehan Sheikh

201,502 views • 1 day ago

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

MAX

13,311 views • 2 months ago

Introducing Wayflow — an embeddable AI workflow builder for your app. Drop in a visual editor where your users build workflows and actually run them. Open source.

Introducing Wayflow — an embeddable AI workflow builder for your app. Drop in a visual editor where your users build workflows and actually run them. Open source.

Taha Shashtari

15,989 views • 4 months ago

OCTOBER’S MOST TRENDING GITHUB REPO: REA (Reverse Engineer Anything). 86.7K ⭐️ on GitHub, +25K just today. It lets your AI agent take apart almost any app and tell you how it works. Free and open source. Here’s the idea: You see a feature you like in some app. You ask your agent “how did they build this?” It digs into the app and explains it to you, with proof, without needing the source code. What it can open: → Mac, Linux and Windows apps → JavaScript and Electron apps → Android apps and websites → Everything runs on your computer, nothing gets uploaded → Works with Claude Code, Codex, Cursor, Gemini CLI and OpenCode Try something like: “Figure out how Discord shows who’s typing in real time, show me the proof, and build something similar for my project.” Heads up: it won’t give you the app’s original code or clone it. And knowing how something works doesn’t mean you’re allowed to copy it. How I’d use it: see how another tool solves a problem I have in my own app, find out which APIs it uses… the rest is up to your imagination. share this if you found it useful ♻️ and save it before you lose it 🔖 Repo ↓

OCTOBER’S MOST TRENDING GITHUB REPO: REA (Reverse Engineer Anything). 86.7K ⭐️ on GitHub, +25K just today. It lets your AI agent take apart almost any app and tell you how it works. Free and open source. Here’s the idea: You see a feature you like in some app. You ask your agent “how did they build this?” It digs into the app and explains it to you, with proof, without needing the source code. What it can open: → Mac, Linux and Windows apps → JavaScript and Electron apps → Android apps and websites → Everything runs on your computer, nothing gets uploaded → Works with Claude Code, Codex, Cursor, Gemini CLI and OpenCode Try something like: “Figure out how Discord shows who’s typing in real time, show me the proof, and build something similar for my project.” Heads up: it won’t give you the app’s original code or clone it. And knowing how something works doesn’t mean you’re allowed to copy it. How I’d use it: see how another tool solves a problem I have in my own app, find out which APIs it uses… the rest is up to your imagination. share this if you found it useful ♻️ and save it before you lose it 🔖 Repo ↓

céline ✧

50,644 views • 1 month ago

The Codiumate-Agent is the first step towards tandem development with your coding agent. It effortlessly slots into your development workflow, helps you be smart about your planning, and offers smart coding completions that make every feature development smoother.

The Codiumate-Agent is the first step towards tandem development with your coding agent. It effortlessly slots into your development workflow, helps you be smart about your planning, and offers smart coding completions that make every feature development smoother.

Qodo

774,204 views • 2 years ago

Introducing terminal-mac. Entire MacOS that runs inside your existing terminal. - Give your agent its own Mac, and keep yours - Watch it work live, next to your terminal - Computer use built in: MCP, CLI and skill - Free & open source

Introducing terminal-mac. Entire MacOS that runs inside your existing terminal. - Give your agent its own Mac, and keep yours - Watch it work live, next to your terminal - Computer use built in: MCP, CLI and skill - Free & open source

govi

717,627 views • 7 days ago

Find your trophies easier and customize them with new plaques and platforms. That and more are coming to Patch 8.4!

Find your trophies easier and customize them with new plaques and platforms. That and more are coming to Patch 8.4!

theHunterCOTW

12,378 views • 1 year ago

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

James Sun

227,571 views • 6 months ago

We wrote up how to find every PHP service you run, including the ones on odd ports, under sub-paths, inside appliances and containers, and how to patch and verify them. Commands plus prompts for your coding agent. We also started It checks Chaos for services running an affected version and emails their security@ inbox for free, with the fix. We are enriching Chaos over the coming months so the next time a bug like this lands, the affected services are mapped fast and remediation starts sooner. Read:

We wrote up how to find every PHP service you run, including the ones on odd ports, under sub-paths, inside appliances and containers, and how to patch and verify them. Commands plus prompts for your coding agent. We also started It checks Chaos for services running an affected version and emails their security@ inbox for free, with the fix. We are enriching Chaos over the coming months so the next time a bug like this lands, the affected services are mapped fast and remediation starts sooner. Read:

ProjectDiscovery

26,202 views • 20 days ago