Security firms have published numerous blog posts describing how they pointed their agent harness at a codebase and found dozens of bugs ( we’re one of them ). However, these posts tend to focus on …
AI Security Roundup
Daily AI security roundup covering malware, vulnerabilities, defensive research, cloud risk, and incident response signals from trusted technical sources.
How Candidates Could Use AI for Good This essay was written with Nathan E. Sanders, and originally appeared in The Guardian . There are plenty of signs that AI will make all of our experiences of the …
Are AIs Still Struggling with CAPTCHAs? Anthropic’s recent security-incident document contains a bit about how CAPTCHAs are still frustrating Claude. > In the transcript, the Claude model that is …
** Ravie Lakshmanan ** Sep 18, 2026 Mobile Security / Malware Cybersecurity researchers have flagged a new Android malware called RatHat that’s assessed to be operated by China-based threat …
** Ravie Lakshmanan ** Sep 18, 2026 Malware / Cybercrime A financially motivated threat actor has been linked to the development and distribution of a JavaScript (JS)-based information stealer known …
** Ravie Lakshmanan ** Sep 18, 2026 Malware / Web Security Cybersecurity researchers have discovered a cluster of 13 npm packages that have been found to deliver a previously undocumented JavaScript …
ai-security
EN
Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents
A flaw in four widely used AI coding agents lets someone who controls a plugin’s code repository swap the plugin an agent installs for a malicious one, even when the agent locked that plugin to …
In July 2025, someone registered a domain that used to belong to a content delivery network. The CDN had been wound down years earlier, and the domain it served assets from was allowed to expire. What …
ai-security
EN
Microsoft Patches CVSS 10.0 Azure AI Foundry Flaw Enabling Unauthorized Privilege Escalation
** Ravie Lakshmanan ** Sep 18, 2026 Vulnerability / Cloud Security Microsoft has released fixes for a maximum-severity security flaw in Azure AI Foundry that could be exploited to achieve privilege …
** Ravie Lakshmanan ** Sep 18, 2026 Malware / Cyber Espionage The Pakistan-aligned threat group tracked as Transparent Tribe (aka APT36 and Earth Karkaddan) has been attributed to a fresh set of cyber …
** Swati Khandelwal ** Sep 18, 2026 Vulnerability / Web Security WordPress today released patches to fix a new set of vulnerabilities in its core software, one of which could allow a crafted web link, …
ai-security
EN
The Self-Expanding Stolen Inference Supply Chain: An AI Agent Harvesting and Re-Serving LLM Access, (Fri, Sep 11th)
Internet Storm Center Sign In Sign Up Handler on Duty: Xavier Mertens Threat Level: green Homepage Diaries Podcasts Jobs Data TCP/UDP Port Activity Port Trends SSH/Telnet Scanning Activity Weblogs …
Apple Updates Everything Published 2026-09-14. Last Updated 2026-09-14 18:33:44 UTC by Johannes Ullrich (Version: 1) 0 comment(s) Today, Apple released its annual update across all its operating …
ai-security
EN
ISC Stormcast For Tuesday, September 15th, 2026 https://isc.sans.edu/podcastdetail/10094, (Tue, Sep 15th)
ISC Stormcast For Tuesday, September 15th, 2026 <https://isc.sans.edu/podcastdetail/10094>
I have not done this type of diary in a while: What traffic will you see from a system on boot, before a user logs in? I just took a quick look at macOS 27 “Golden Gate” to see what …
Earlier today, I noted an odd request showing up in our “First Seen” report: GET /PIAF-HMS/ HTTP/1.1 Host: [redacted] User-Agent: Farez-Sorter/1.0 Accept-Encoding: gzip This request is …
ai-security
EN
ISC Stormcast For Wednesday, September 16th, 2026 https://isc.sans.edu/podcastdetail/10096, (Wed, Sep 16th)
ISC Stormcast For Wednesday, September 16th, 2026 <https://isc.sans.edu/podcastdetail/10096>
ai-security
EN
ISC Stormcast For Thursday, September 17th, 2026 https://isc.sans.edu/podcastdetail/10098, (Thu, Sep 17th)
Internet Storm Center Sign In Sign Up Handler on Duty: Xavier Mertens Threat Level: green Homepage Diaries Podcasts Jobs Data TCP/UDP Port Activity Port Trends SSH/Telnet Scanning Activity Weblogs …
The consumer data broker Radaris.com has long had a reputation for ignoring requests to remove personal information from its vast empire of people-search services online. That reputation caught up …
1Password’s FLAWED report , published on August 6, 2026, gives defenders a misleading picture of AI patching. Its headline says models produced clean fixes only 26% of the time. That figure includes …
My Talk at DEF CON Last month, I gave a talk at DEF CON on AI hacking: what happens when AIs become hackers. It’s a combination of the potentialities I raised in my 2022 book A Hacker’s Mind and the …
Friday Squid Blogging: Rotting Squid on a Beached California Boat Smells awful : > But an estimated 30 to 50 tons of dead squid remain inside the boat’s catch tank, where they have been decomposing …
Using AI for Weapons Development Last week, Anthropic released a long and detailed document describing current misuses of their Claude models. I’m still reading it, but I wanted to flag this: > We …
Microsoft’s Patching Once a month, Microsoft pushes a security update to all Windows users. Tomorrow’s is a new record : > Microsoft’s patch for September is a doozy, with a record number of …
Upcoming Speaking Engagements This is a current list of where and when I am scheduled to speak: I’m speaking online (via Zoom) at a League of Women Voters event on Tuesday, September 22, 2026 at 5 PM …