AI, AI, AI and ... AI
LLMs versus ImageMagick: an interesting walkthrough with some cool details about ImageMagick behaviours. ImageMagick: From Arbitrary File Read to File Write In Every Policy.
A good introduction on how to get started with code review using Claude: Leveling Up Secure Code Reviews with Claude Code.
Probably the article worth reading this week, whether you agree or not, at least you will get to think about it Vulnerability Research Is Cooked.
Trail of Bits is probably the best example of security consulting team deploying AI and sharing about it. Make sure you read this one. How we made Trail of Bits AI-native (so far).
Claude vs FreeBSD, this one even includes the prompts used: MAD Bugs: Claude Wrote a Full FreeBSD Remote Kernel RCE with Root Shell (CVE-2026-4747).
A bit of a long read but so much shared in this post. Grab a coffee and read through it! Jenny was a Friend of Mine - MCPs and Friends.
📬 Never Miss Quality Security Research
Get these curated picks delivered to your inbox every week:
- Hand-picked vulnerability research
- Practical security insights
- CVE deep-dives worth your time
- No fluff, just signal
Want to build these skills hands-on?
PentesterLab has 700+ real-world labs on web hacking, code review, and vulnerability analysis. Start with a free account.
