Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.
Search across headline titles and summaries.
Weekly headline count for the current query.
Ask an AI agent to summarize the reviews on a product page, and a single planted review can make it click "Buy Now" instead. Ask a coding assistant to apply a maintainer's fix from a GitHub thread, and a fake comment can make it run a stranger's command on your computer
Also, 23andMe Breach Settlement, GitHub AI Flaw, Ubiquiti Patches Critical BugsThis week, hidden breaches, researchers exposed a GitHub AI agent flaw, an Ubiquiti critical flaw, a ColdFusion flaw, a growing Chinese ORB, U.K. government FortiBleed exposure, 23andMe victims get $46.75 million, 3.8 million affected by Medtronic breach and Cerner's 2025 victim count went up.
More fun with AI jailbreaks, this time at the workflow level
An AI coding assistant that refuses to answer a dangerous request in its chat box can answer it anyway if the same request is broken into small, ordinary-looking steps inside a code editor. That is the finding of a new study of GitHub Copilot by researchers Abhishek Kumar and Carsten Maple
Per usual, there's no fix – or even any documentation – for GitLost
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious payload that remains invisible to security scanners, AI agents, and human reviewers. [...]
Cybersecurity researchers have disclosed details of four vulnerabilities in Dify, an open-source agentic workflow platform with more than 146,000 GitHub stars, that could allow attackers to stealthily read artificial intelligence (AI) conversions from other customers' applications without requiring authentication
A Rust crypto clipper hides behind fake GitHub stars and AI-narrated YouTube videos
Microsoft-Owned GitHub, Which Runs npm, Previews Supply-Chain Security FixesThe popular Mastra AI framework, used to build artificial intelligence agents, workflows and retrieval-augmented generation pipelines, has been poisoned by attackers, and Microsoft-owned GitHub has advised all developers to downgrade Mastra, pending compromised packages being found and eradicated.
An unknown threat actor has been observed leveraging paid or promoted posts on legitimate news websites to drum up buzz for their warez, according to new findings from Check Point Research
The Miasma worm compromised 73 Microsoft GitHub repos, spreading via AI coding tools and stealing cloud credentials from developers and CI/CD systems. A self-replicating worm called Miasma has compromised 73 Microsoft GitHub repositories and forced GitHub staff to disable them. The affected repos include core Azure infrastructure like azure-functions-host and the entire Durable Task family […]
Monday again. The weekend was meant to be quiet. It wasn't. Last week had poisoned packages, a broken AI helper, and a worm tearing through repos. The ugly part: basic tricks still worked
Microsoft Threat Intelligence identified a prompt injection pathway in Claude Code GitHub Action that allowed access to workflow secrets under specific conditions. This research examines the attack chain, responsible disclosure process, Anthropic's mitigation, and guidance for securing AI-powered CI/CD workflows. The post Securing CI/CD in an agentic world: Claude Code Github action case appeared first on Microsoft Security Blog.
A security researcher found a flaw in Anthropic's Claude Code GitHub Action that let an attacker take over vulnerable public repositories running it, with nothing more than a single opened GitHub issue. Because Anthropic's own action repo used the same workflow, a working attack could have pushed malicious code into the action itself and onto the projects downstream that pull it
Cybersecurity researchers have disclosed details of a new malicious supply chain campaign that's targeting developers using OpenAI Codex through a legitimate-looking remote web UI
Sloppy AI-generated npm infostealer leaked its own GitHub token, exposing the operator
Cybersecurity researchers have discovered a new malicious package on the npm registry that comes with information stealing capabilities
Malicious npm Package Lets Attackers Capture Refreshed TokensA researcher has mapped a five-step attack on Claude Code that intercepts the credentials giving AI agents access to Jira, GitHub and Confluence, and demonstrated that the standard incident response move, rotating the stolen token, hands the attacker a fresh one.
Healthcare giant's maintainers handed May deadline to enact the change The UK's National Health Service (NHS) is ordering all of its technology leaders to temporarily wall off the organization's open source projects over concerns relating to advanced AI and Anthropic's Mythos.…
This week, the shadows moved faster than the patches