惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Stack Overflow Blog
Stack Overflow Blog
S
SegmentFault 最新的问题
大猫的无限游戏
大猫的无限游戏
The GitHub Blog
The GitHub Blog
M
MIT News - Artificial intelligence
T
Tailwind CSS Blog
aimingoo的专栏
aimingoo的专栏
Last Week in AI
Last Week in AI
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
罗磊的独立博客
H
Help Net Security
Engineering at Meta
Engineering at Meta
Microsoft Security Blog
Microsoft Security Blog
阮一峰的网络日志
阮一峰的网络日志
J
Java Code Geeks
T
The Blog of Author Tim Ferriss
Hugging Face - Blog
Hugging Face - Blog
C
Check Point Blog
F
Fortinet All Blogs
腾讯CDC
博客园 - Franky
WordPress大学
WordPress大学
U
Unit 42

Aikido Security's Blog

Axios CVE-2026-40175: a critical bug that’s… not exploitable GlassWorm goes native: New Zig dropper infects every IDE on your machine Aikido Attack finds multiple 0-days in Hoppscotch The cybersecurity doomerism around Mythos doesn't match what we see on the ground axios compromised on npm: maintainer account hijacked, RAT deployed Popular telnyx package compromised on PyPI by TeamPCP Aikido × Lovable: Vibe, Fix, Ship CanisterWorm Gets Teeth: TeamPCP's Kubernetes Wiper Targets Iran TeamPCP deploys CanisterWorm on NPM following Trivy compromise Security testing is validating software that no longer exists Aikido Recognized by Frost & Sullivan with the 2026 Customer Value Leadership Award in ASPM GlassWorm Hides a RAT Inside a Malicious Chrome Extension fast-draft Open VSX Extension Compromised by BlokTrooper Glassworm Strikes Popular React Native Phone Number Packages Glassworm Is Back: A New Wave of Invisible Unicode Attacks Hits Hundreds of Repositories How Security Teams Fight Back Against AI-Powered Hackers Introducing Betterleaks, an open source secrets scanner by the author of Gitleaks Trump’s 2026 cybersecurity strategy: From compliance to consequence How does AI pentesting work with compliance? What continuous pentesting actually requires Rare Not Random: Using Token Efficiency for Secrets Scanning Persistent XSS/RCE using WebSockets in Storybook’s dev server Why Determinism Is Still a Necessity in Security WAF vs. RASP vs. ADR Introducing Aikido Infinite: A new model of self-securing software How Aikido secures AI pentesting agents by design Astro Full-Read SSRF via Host Header Injection How to Get Your Board to Care About Security (Before a Breach Forces the Issue) What is Slopsquatting? The AI Package Hallucination Attack Already Happening SvelteSpill: A Cache Deception Bug in SvelteKit + Vercel
AI as a Power Tool: How Windsurf and Devin Are Changing S...
2025-11-06 · via Aikido Security's Blog

We brought together Ian Moritz, Deployed Engineer at Cognition, and Mackenzie Jackson from Aikido Security for a live masterclass on AI-assisted coding.

The goal wasn’t to hype new tools. It was to talk about how developers can stay in control while AI starts writing, testing, and securing code beside them.

AI coding isn’t good or bad. It depends on how you use it.

When asked whether AI coding helps or hurts security, Ian didn’t take a side. He explained that it comes down to how you use it.

“You can make arguments either way. What matters is how fast it’s improving. Models are getting better at avoiding vulnerabilities, and we’re learning how to use them responsibly.” - Ian Moritz, Cognition

He compared AI to a power tool. Useful, but dangerous if you’re careless.

“Treat AI like a power tool. You still need intent, control, and review.” - Ian Moritz, Cognition

AI is speeding up development, but it still needs humans to set direction and check the work.

Seeing your system is half the battle

Good security starts with understanding how your app actually behaves.

Windsurf was built to give developers that visibility.

“Understanding how data moves through your system is half of security. The rest is knowing where it shouldn’t go.” - Ian Moritz, Cognition

Using Deep Wiki and Code Maps, developers can trace how functions connect, where data travels, and what could break if something changes.

Instead of digging through thousands of lines, you can map the flow and spot weak points fast.

Security that sits where you build

During the demo, Mackenzie showed how Aikido’s extension for Windsurf finds security issues inside the IDE itself.

It flags exposed secrets, vulnerable dependencies, and missing security headers as soon as you save the file.

“This is where security belongs. Inside the IDE, before it ever becomes someone else’s problem.” - Mackenzie Jackson, Aikido Security

It’s feedback that fits into a developer’s workflow. No waiting for CI scans or security audits. You catch issues early, fix them quickly, and keep building.

Agents that test your code for you

Ian shared what’s next for tools like Windsurf and Devin.

He sees a future where AI doesn’t just write code, it tests it too.

“The cost of high-quality testing is dropping fast. We’ll run more tests, not fewer.” - Ian Moritz, Cognition

Devin is designed to act like a red team in the background. It can analyze your codebase, simulate attacks, and flag risky logic before deployment.

Instead of waiting for vulnerabilities to show up in production, developers will be able to stress-test their own work automatically.

The future developer

Ian closed with advice for developers learning to work with AI tools.

“Spend a little time learning Git. Break work into small pieces. Let agents help with the rest.” - Ian Moritz, Cognition

Developers will spend less time typing code and more time reviewing, testing, and guiding AI systems. The skill that matters most is not speed. It’s awareness. Knowing what your code does, why it exists, and where it could break.

AI-assisted coding isn’t about replacing developers. It’s about giving builders better tools that think fast but still need human judgment.

The best developers will be the ones who stay close to their code, understand their systems deeply, and never hand over control.

Watch the full Masterclass.