It's great that a class of tool that by its very design is an unfixable security issue is forced into everything: «This works often enough that Måløy reported this to Microsoft as a security hole in March. He gave them a 90-day reporting window, Microsoft extended that twice to a total of 144 days, and they still didn’t have a solid fix. So Måløy posted about the hole on July 28th.» Copilot prompt injection goes viral in your documents https://pivot-to-ai.com/2026/08/03/copilot-prompt-injection-goes-viral-in-your-documents/
Copilot prompt injection goes viral in your documents
All systems based on chatbots can be prompt injected. You can always tell the bot to do things it shouldn’t. The AI vendors try to put in guard rails. The guard rails sort of work for about two sec…
Microsoft says Copilot is for entertainment purposes only, not serious use — firm pushing AI hard to consumers and businesses tells users not to rely on it for important advice
These might be boilerplate disclaimers, but they kind of contradict the company's ads and marketing.
AI Is Killing Microsoft
Microsoft's AI assistant, Copilot, is struggling to show traction, causing the tech giant to continue falling behind. Investors are not happy.
It's Time To Leave Microsoft
Contrary to what you might believe from the title, this article isn't published to try to convince you to leave Microsoft (although, if you are still on the fence, please continue reading the section below); instead of providing you with a paralyzing amount of dystopian information that is already available
Snowflake Cortex AI Escapes Sandbox and Executes Malware
PromptArmor report on a prompt injection attack chain in Snowflake's Cortex Agent, now fixed. The attack started when a Cortex user asked the agent to review a GitHub repository that …
Assessing Claude Mythos Preview’s cybersecurity capabilities
Claude Mythos Preview is a new general-purpose language model that is strikingly capable at computer security tasks. This post provides technical details for researchers and practitioners who want to understand exactly how we have been testing this model, and what we have found over the past month.
Just a rumour of a bug is enough to find a security exploit these days
Thinking through how the conventional OSS security embargoes no longer buy us time, and what open source maintainers might do instead to respond
Investigating three real-world incidents in our cybersecurity evaluations
In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.
Glassworm Returns: Invisible Unicode Malware Found in 150+ GitHub Repositories
The Glassworm supply chain attack is back. Researchers uncovered malware hidden in invisible Unicode characters across 150+ GitHub repositories, plus npm packages and VS Code extensions.
COMPOST Special Issue: Stop Surveillance Copaganda
Anti-surveillance stories, reactions, analysis, and incitement built by privacy activists and human rights experts, in collaboration with Strange Horizons as well as the DWeb Camp, DragonCon, and RightsCon communities. The toolkit is now available globally and for free to all creators who want to write more dynamic stories that challenge fascist repression via surveillance tech.
Exposed Moltbook Database Let Anyone Take Control of Any AI Agent on the Site
'It exploded before anyone thought to check whether the database was properly secured.'
You're Invited: Delivering malware via Google Calendar invites and PUAs
Threat actor used malicious Google Invites and hidden Unicode “Private Use Access” characters (PUAs) to brilliantly obfuscate and hide a malicious NPM package.
.png)
‘Doom Loop’: OpenAI and Microsoft Admits LLMs Are Destroying the Web and Built on Theft
"Millions of people around the world will soon consider large models ‘hoovering up’ all their work to be an astonishing theft of unprecedented proportions."
Prompt Injection as Role Confusion
First, I absolutely love this: This is a blog-style writeup of the paper. I wish every paper would come with one of these. Academic writing is pretty dry - the …
Zack Whittaker (@zackwhittaker@mastodon.social)
Another AI test gone awry, U.K. edition. "An agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering — creating fake online identities and using them to pressure the project's maintainer to approve the code." More: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
Muse, Meta's extraordinarily privileged AI assistant, has a serious 0-day
A simple ClickFix attack is only one way to completely hijack the new agent.
