The AI Front Page

Topic Edition

Security

30 stories from 8 sources across 1 topics.

Stories

30

Sources

8

Topics

1

For You lens

15 stories in this edition match your reader profile.

Reader signals

3

Searches

0

Matches

15

Top score

106

Tune For You

Edition Index

Topic, entity, and source map

Topics

Security30 stories

Entities

OpenAI11 storiesAnthropic10 storiesClaude6 storiesHugging Face5 storiesMicrosoft4 storiesGoogle2 stories

Sources

Hacker News AI14 storiesSimon Willison LLMs4 storiesTechCrunch AI3 storiesArs Technica AI2 storiesAWS Machine Learning Blog2 storiesThe Decoder2 stories

Simon Willison LLMs / 6:43 PM

AI Worming through Word

AI Worming through Word Neat new prompt injection variant by Håkon Måløy, who found a way to upgrade prompt injection attacks against Microsoft Word to full self-replicating worms: An attacker places hidden instructions in a document that is later used as source material in Copilot for Word. Copilot may interpret those instructions as part of the user’s request, causing it to manipulate the document being drafted or edited. Copilot may then also copy the hidden instructions into the resulting document, turning that document into a new carrier. If the carrier is subsequently used in another Copilot-assisted workflow, the instructions can trigger again and propagate into further documents, even without the attacker’s original document being present. We've seen plenty of hidden white-on-white text before - the kids are using it in their job applications now - but this is the first one I've seen that deliberately copies instructions to self-replicate itself. It was responsibly disclosed to Microsoft who then had 144 days to work on a fix, but so far (unsurprisingly) there's no mitigation that covers the full class of attack. Via Hacker News Tags: microsoft , security , ai , prompt-injection , generative-ai , llms

ReadSource

Simon Willison LLMs / 6:18 PM

Quoting Matthew Green

Right now we’re in the midst of a historic transition from traditional public-key algorithms based on EC-based cryptography and RSA, moving over to new post-quantum algorithms based on novel problems. This is why there are so many standards like HAWK being considered. If there was ever a perfect time for a massive new public cryptanalysis capability to come on line, we’re in it. So unless AIs succeed in undermining all of our hard problems altogether (or we live in Impagliazzo’s Minicrypt ) then this could not be a better time for AI to get good at cryptanalysis. In the best case, the result is that we gain real confidence in the problems we’ve identified, and the cryptanalysis literature gets a lot more robust. Hopefully. — Matthew Green , on Anthropic's recent cryptography work Tags: cryptography , ai , generative-ai , llms , anthropic , claude , ai-security-research , claude-mythos-fable

ReadSource

The Decoder / 4:26 PM

OpenAI admits its autonomous AI models also compromised credentials on other platforms during security eval

During a security evaluation, OpenAI's autonomous hacking models broke into Hugging Face and used exposed credentials on four other services. Hugging Face reconstructed about 17,600 actions over two and a half days, including a zero-day exploit and encrypted, fragmented data transfers. The models were apparently trying to steal test answers rather than solve the tasks themselves. The article OpenAI admits its autonomous AI models also compromised credentials on other platforms during security eval appeared first on The Decoder .

ReadSource

Microsoft AI Blog / 3:21 PM

Looking back on Microsoft’s FY26: From AI experimentation to Frontier Transformation

Throughout this past fiscal year, customers across every industry and segment moved from AI experimentation to deploying AI for real-world business outcomes. They unlocked innovation and created new opportunities for growth. The post Looking back on Microsoft’s FY26: From AI experimentation to Frontier Transformation appeared first on The Microsoft Cloud Blog .

ReadSource

The Decoder / 11:50 AM

OpenAI open-sources Codex Security CLI to help developers find and fix vulnerabilities from the command line

OpenAI has released Codex Security CLI, an open-source tool that automatically detects and fixes vulnerabilities in code repositories. Previously known internally as "Aardvark," the system has already helped fix more than 3,000 critical security flaws, according to OpenAI. It competes directly with Anthropic's Claude Security, as both AI companies race to match the growing automation of cyberattacks with AI-powered defense. The article OpenAI open-sources Codex Security CLI to help developers find and fix vulnerabilities from the command line appeared first on The Decoder .

ReadSource

The Verge AI / 11:00 AM

We’re running out of reasons to ignore AI safety

Earlier this month, OpenAI gave several of its AI models a task: complete a test designed to measure their cybersecurity capabilities. It put the systems in a sandboxed environment without an internet connection and set them off to work. What happened next is almost laughably silly - but also, as Adam Gleave, cofounder and CEO […]

ReadSource

AWS Machine Learning Blog / 5:00 PM

Evaluating AI Agents: A production blueprint with Strands and AgentCore

Together, Motorway and AWS built an end-to-end evaluation pipeline that reduced incorrect results from 1 in 8 queries to 1 in 50 and cut issue detection time from few hours to few minutes. The pipeline combines the Strands Agents SDK with Amazon Bedrock AgentCore, a fully managed service for deploying and operating AI agents at scale. In this post, you will learn how to build this pipeline for your own agents.

ReadSource

Simon Willison LLMs / 10:45 PM

Discovering cryptographic weaknesses with Claude

Discovering cryptographic weaknesses with Claude The best part of this article (here's the repo ) about how Anthropic researchers used Claude Mythos to find mathematical flaws in both HAWK and a weaker version of AES ("neither of these results has a practical impact on today’s computer systems") is the prompts that they shared, spelling mistakes included: the models tend to think it is impossible to solve so they don't try they need a good amount of prompting. why not do aes-128 r7? the whole point is to find something better than existing approaches. no again the goal is that we have highly inteligent model as good top researcher, we want to find new attacks no we don't want to change the targets [...] agian we need to find something that worth publishing again we are not looking for low hanging fruit, we want proper research to find genuinly hard findings. Mythos Preview worked for 60 hours in total (~$100,000 in estimated API cost) and the main human interventions were to encourage it not to give up and "find something that worth publishing". The paper CryptanalysisBench: Can LLMs do Cryptanalysis? describes the new eval that was created as part of this work, in partnership with ETH Zurich, Tel Aviv University, and University of Haifa. Via Hacker News Tags: ai , prompt-engineering , generative-ai , llms , anthropic , claude , ai-security-research , claude-mythos-fable

ReadSource

Simon Willison LLMs / 9:28 PM

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident Hugging Face just released this extremely detailed technical description of OpenAI's recent accidental cyberattack against their infrastructure . This attack was very sophisticated, and the resulting document doubles as a crash-course in modern adversarial security approaches. We're still waiting for more details from OpenAI on how their agent broke out of its sandbox. The package proxy that it found a zero-day vulnerability in has now been confirmed as JFrog's Artifactor, and JFrog and OpenAI Collaboration on Zero-Day Security Findings from JFrog links to the Artifactory 7.161.15 release notes which list 8 separate CVEs credited to OpenAI staff members. Having broken out through the HTTP proxy, the agent started by establishing a base of operations for the rest of the attack: [...] the agent escaped its sandbox by exploiting a zero-day in the package registry cache proxy, one of its primary permitted network egress with internet, then abused a public code-evaluation external sandbox hosted on a third-party provider's infrastructure. It was able to run commands as root/admin on that external sandbox and used it as a control, staging, and egress base for the entire campaign: it acted as an external launchpad for the agent. (That "third-party provider" turned out to be Modal .) It then spent five days - from Thursday 8th to Monday 13th July - executing a classic attack pattern: establishing C2 (command and control), reconnaissance, escalating privileges, dumping configuration information, exfiltrating the target data, and cleaning up after itself. (The first Hugging Face post about the incident followed on Thursday 16th , and OpenAI's confession came on Tuesday 21st .) Along the way it used all kinds of neat tricks. At one point it found an unsafe Jinja2 template execution and used it to execute arbitrary code: {{ cycler.__init__.__globals__.__builtins__.exec( "import gzip,base64; exec(gzip.decompress(base64.b64decode('<payload>')))" ) }} It broke out of a container within Hugging Face, stole a Kubernetes service-account token, and used that to further explore the network. It monkey-patched the Python socket library to hard-code an IP address when "DNS got in the way": socket.getaddrinfo = lambda *a, **k: [(2, 1, 6, '', ('<pinned-ip>', 443))] It even fired up its own Tailscale network to help exfiltrate data! tailscaled --tun=userspace-networking \ --state=mem: --socket=/tmp/ts.sock \ --socks5-server=127.0.0.1:1055 \ --no-logs-no-support >/tmp/td 2>&1 & The Hugging Face team note that, while a human attacker could have discovered and used the same exploits, the key difference here was speed : Our learning from this type of attack is that machine-speed offense makes ordinary weaknesses more expensive for defenders. LLM agents bring a step increase in the number of paths an attacker can test, the speed at which failed paths can be replaced, and the volume of evidence defenders must interpret. What's clear to me from this is that the very best frontier models, unencumbered by additional guardrails, will find an exploit if there is one to be found. The entire software industry needs to up its security game. Tags: jinja , python , security , ai , openai , generative-ai , llms , hugging-face , coding-agents , ai-security-research , openai-hugging-face-incident

ReadSource

Latest story in this edition: 11:01 AM

Back to front page