0.56
new ep is out with @MrJoeyMelo where he shows me how to jailbreak AI chatbots using roleplaying, token splitting, prompt injection and more. https:// youtu.be/BehGpUB-frc
Official intelligence summary
HAIJA INTEL REPORT
Generated 21/04/2026, 09:08. Pipeline: Europe/Belgrade. Regular sources favor exploit, blog, red-team, and attack-path content. CVE items only stay with exploit signal.
Total items15
Regular sources5
Tweets / X10
Threshold0.62
You can save this report in your browser with the favorite button. If you need a shared favorite list, use the CLI helper.
Tweets / X
10 items
0.46
Here is another reason why you should move your bug bounty program from the Hackerone platform Lovable has a mass data breach affecting every project created before november 2025. I made a lovable account today and was able to access another users source code, database credential
0.45
Discover Unit 42’s learnings from getting hands-on with frontier AI models. We illustrate an AI-enabled attack path from recon and initial access to exfil and documentation. Learn what you should do right now to not be outpaced by AI-assisted adversaries: https:// bit.ly/3Qx43Xu
0.43
New Hacktivist DDoS Dashboard is live! Track actor claims, botnet C2, & victim trends in Google TI via Dashboards. https:// bit.ly/4cC5Qlo #GoogleTIMondays #DDoS
0.39
AI unlocks innovation, but it also expands the attack surface. We’ve adapted findings from our recent Mandiant AI Red Team engagements into a technical roadmap for securing AI. Learn to map the AI attack surface, apply multi-layer controls, and more. https:// bit.ly/3QOlgvA
0.39
Anthropic's Mythos makes one thing clear: Frontier AI is collapsing the exploit window. The CrowdStrike 2026 Global Threat Report shows why this matters: Zero-day vulnerabilities exploited before public disclosure rose 42%, and attacks by AI-enabled adversaries increased 89%
0.39
Vercel hacked via compromised AI customer, @nahuelrm_ takes MVH plus Erradicator at H1-361, @valent1nee takes the MVH from Google, @BRuteLogic audits autonomous AI vuln discovery claims, and @S1r1u5_ reports a Claude-assisted V8 exploit against Discord that hit a shell after
0.38
What happens when Sara Pentest gets six hours with a live application? Synack AI Engineers Jack Hall and James Thatcher break it down in our latest blog: https:// synack.com/blog/sara-pent est-ai-finds-sql-injection-account-takeover-xss/?utm_campaign=5710593-Pentesting-AI-FY26&ut
0.32
Am I a crazy old man because I want articles to be written by a human and have it sound like a human? AI slop comes across so fucking lazy. It's like, if you can't even put in the bare minimum effort of writing a malware analysis paper, how can we take you seriously? I don't
0.32
The model inflection point is around the corner. Minimax, GLM, and Kimi are performing at Opus 4.5 golden-days levels. Tbh that's the point where i felt AI could really offload and help with in depth research and dev. Excited.
Regular sources
5 itemsVercel Employee's AI Tool Access Led to Data Breach
Stolen OAuth tokens, which are at the root of these breaches, "are the new attack surface, the new lateral movement," a researcher noted.
Building the agentic cloud: everything we launched during Agents Week 2026
Agents Week 2026 is a wrap. Let’s take a look at everything we announced, from compute and security to the agent toolbox, platform tools, and the emerging agentic web. E…
Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain
Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture that could pave the way for remote code exec…
The GNU C Library security advisories update for 2026-04-20
Posted by Carlos O'Donell on Apr 20 The following security advisories have been published: GLIBC-SA-2026-0008: =================== Static buffer overflow in deprecated n…
Re: Go 1.26.2 and Go 1.25.9 are released with 10 security fixes
Posted by Demi Marie Obenour on Apr 20 I wonder if build infra needs to be updated to support automated rebuilds when a reverse dependency is updated. My understanding i… | Posted by Morten Linderud on Apr 20 We don't. I originall did this work a few years ago but it just produced a huge list of packages that would need to be worked through…