Oasis Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden …
AI Security Roundup
Daily AI security roundup covering malware, vulnerabilities, defensive research, cloud risk, and incident response signals from trusted technical sources.
ai-security
EN
ISC Stormcast For Thursday, August 20th, 2026 https://isc.sans.edu/podcastdetail/10060, (Thu, Aug 20th)
ISC Stormcast For Thursday, August 20th, 2026 <https://isc.sans.edu/podcastdetail/10060>
ai-security
EN
Using Microsoft Graph and Powershell to Mine for Information - Stale Accounts and Licenses, (Thu, Aug 20th)
Microsoft Graph is a newer API that is meant to replace several others. OK, it’s at version 2.3.9, so it’s not all that new, but it’s new enough that lots of folks (and commercial …
Building on the last diary on Using MS Graph and Powershell, let’s look at “Risky” logins. Risky logins are a derived set of parameters that look at various (you guessed it) risky …
ai-security
EN
Even MOAR Powershell, looking at Entra logins - the good, the bad and the password sprays, (Fri, Aug 21st)
One thing that folks never seem to do after “going to the CLOOOOUUUUD” is to look at their logs, logs that they would have checked daily when things were on premise. One log that really …
ai-security
EN
Who Got Missed in the MFA Rollout? More Powershell + Graph + Entra scripting!, (Fri, Aug 21st)
In every MFA rollout, there will come a time where you think you are closing in on “done”, and some automation to list what’s left would be handy. Something quicker than scrolling …
ai-security
EN
ISC Stormcast For Friday, August 21st, 2026 https://isc.sans.edu/podcastdetail/10062, (Fri, Aug 21st)
ISC Stormcast For Friday, August 21st, 2026 <https://isc.sans.edu/podcastdetail/10062>
ai-security
EN
ISC Stormcast For Monday, August 24th, 2026 https://isc.sans.edu/podcastdetail/10064, (Mon, Aug 24th)
ISC Stormcast For Monday, August 24th, 2026 <https://isc.sans.edu/podcastdetail/10064>
Every Signal chat starts the same way: the client asks the Signal server for the public key associated with your contact’s phone number. But how do you know the server gave you the right key? A …
New malware that uses steganography always gets my attention, but I was disappointed when I looked at the latest DOUBLECUP write-up . It doesn’t use real steganography: You can see the …
It can be daunting to determine who’s responsible for showing ads on the websites we visit, or who’s harvesting data from the mobile apps we use every day. That information is already semi-public, but …
Microsoft today released updates to remedy at least 398 security vulnerabilities in its Windows operating systems and supported software, including one weakness that is already being actively …
LLMs and Contextual Integrity I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic. “ CIMemories: A Compositional Benchmark …
Police Are Hiding Their Use of Flock Surveillance Cameras A usage policy for Flock license plate reader cameras tells police not to talk about the cameras: > When cops use Flock to arrest someone …
ICE Collecting DNA Samples ICE collected nearly a million DNA samples last year. Tags: databases , DNA , FBI , homeland security , identification , national security policy Posted on August 19, 2026 …
More Incidents of AIs Going Rogue in Cybersecurity Challenges The AI Security Institute has a new report of AI systems engaging in “unsanctioned behavior”—what I have been calling “ genie behavior …
Friday Squid Blogging: Neon Flying Squid The neon flying squid can fly in formation. > The shoal of about 100 squid rose unexpectedly from a patch of the Pacific Ocean around 370 miles from Tokyo …
Detailed Timeline of OpenAI’s Cyberattack on Hugging Face OpenAI presented details of its AI’s model’s cyberattack on Hugging Face at Black Hat last week. Simon Willison details the timeline. It’s …
AI Is Learning to Write Genetic Code This sort of research is both exciting and terrifying: > The two models in question were told to generate complete genomes for a viable bacteriophage—a type of …
Criminal Deception in Silicon Valley Interesting paper : > Abstract: > With entrepreneurial fraud cases on the rise, we investigate how entrepreneurs carry out > criminal deception > , …
ai-security
EN
UAT-10147 Uses AI to Scale Server Attacks, Deploys SPECTRE With EDR Bypass and Linux Rootkit
Cybersecurity researchers have disclosed details of a Chinese-speaking cybercrime group dubbed UAT-10147 that’s targeting Windows and Linux web servers globally across the education, media, …
Big security risks come in small packages. While enterprise security teams focus on policing the proliferation of employees using ChatGPT and Claude for quick drafting tasks, a more urgent threat is …
Cybersecurity researchers have flagged two new malware families called WordlistLoader and SynkLoader that’s used to deliver next-stage payloads and likely sell access to ransomware groups. …
** Ravie Lakshmanan ** Aug 24, 2026 Cyber Espionage / Cyber Attack Cybersecurity researchers have flagged a cyber espionage campaign targeting Myanmar that uses graduation ceremony invitation lures to …
ai-security
EN
Critical Keycloak Password Reset Flaw Could Let Unauthenticated Attackers Take Over Any Account
** Swati Khandelwal ** Aug 24, 2026 Vulnerability / Identity Security Red Hat and the Keycloak project have released patches to address a critical security flaw in the open-source identity and access …