Jots and thoughts from a cybersecurity enthusiast
SpecterOps released a paper on their Pass-the-Passkey presentation from Black Hat, with a family of 15 Passkey-related attacks. Long story short, most issues are based on two premises The attacker relies on a compromised device with access to those passkeys, which is already a higher bar than
The latest video from AI Explained as well as OpenAI's Blackhat talk about the Hugging Face hack are fascinating to go through. A few notes: The UK AI Security Institute (AISI) released a report on their own cybersecurity issues when they ran benchmark with frontier AI models. Keep
Excellent, detailed article by Figma security engineers on how they stay ahead of vulnerabilities with agents . Let's start with the key vocabulary you need to know to understand the rest of the article: Precision is the share of reported findings that are real vulnerabilities. High precision implies low
Alex Wauters recently commented the results of a game he published a few months ago, where the player has to review approval requests from a fictitious Claude Code session . While this was just a game and not a proper research experiment, the sample size is significant (over 40,000 runs)
As part of their newly created “Agent Week”, Cloudflare published interesting titbits about how they addressed the exploding demand for AI-assisted workloads internally, embracing innovation while keeping a proper security posture. They released Cloudflare OS , a misleading name for what looks like an Open Source, Cowork-like
Microsoft published a detailed analysis of the new ChainDrop supply chain attack affecting NPM packages and adopting self-replicating, worm behaviour, similar to Shai-hulud: The malware typically executes automatically through an npm preinstall lifecycle hook before package installation completes. Once executed, the malware searches developer workstations and continuous integration
Interesting side effects of everyone going ham with LLM-based security scans. Someone released security advisories for SQLite , which the NIST National Vulnerability Database ( NVD ) promptly registered as CVE with a “Critical” CVSS score, acknowledged by CISA as an Authorized Data Publisher, yet security researchers were not able
Google recently released a research article on Beyond Zero: Enterprise security for the AI era . If the name Beyond Zero sounds familiar, it's because this is a mix of Zero Trust and Beyond Corp , Google's own spin of Zero Trust Architecture (ZTA). Announced in a paper
I just stumbled upon an excellent 3-parts series of (responsibly disclosed) attacks impacting Microsoft Copilot. The first one is poisoning Copilot memory via an attacker-controlled webpage, which allowed the instruction to gain persistence in the victim's ecosystem. As explained in the SociaLLM article, there is only
After Microsoft's own release of Project Perception , I'm seeing a lot of cybersecurity-focused harnesses popping as open source. One of the oldest and most well known is Strix , which I initially thought was all about offence with vulnerability discovery and exploitation, but seems to also
Cybersecurity is the new trendy topic to cover with LLM and Microsoft wants to be part of the party : Today we’re announcing MAI-Cyber-1-Flash inside of MDASH, our multi-agent vulnerability identification and remediation harness. Together they deliver world-class performance at 50% of the cost
Cybersecurity awareness isn't useless, but it's often overrated. Organizations achieve better outcomes by designing systems that tolerate human error instead of depending on flawless user behaviour.
Anthropic just released Opus 5 , with some good news for the cybersecurity teams. The cybersecurity safeguards will be more lax and let us use the model for some defence tasks as Anthropic is confident for its lack of skill in executing offensive ones like creating exploits: As with its predecessor,
Remember the security incident from Hugging Face I mentioned in the asymmetry problem ? Turns out the “autonomous AI agent” responsible for the attack wasn't coming from some random cybercriminals but some OpenAI models running wild, trying to cheat their way into higher benchmark score : Last week,
HuggingFace just experienced a very common problem with cybersecurity safeguards in general audience tooling : it only hinders the good guys on the defence side. In their July 2026 Security incident disclosure , when they tried to leverage their AI-assisted tool set for forensics analysis, they quickly hit a brick wall