aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

Browse All

All tracked items across vulnerabilities, news, research, incidents, and regulatory updates.

to
Export CSV
9514 items

CVE-2026-58116: LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to ex

criticalvulnerability
security
Jun 30, 2026
CVE-2026-58116

LLaMA-Factory (a tool for customizing large language models) versions up to 0.9.5 has a remote code execution vulnerability where attackers with access to the web interface can run malicious code by providing a fake model path in the Chat or Training sections. The vulnerability exists because the application doesn't validate user input before passing it to code that loads models, and it uses a setting called trust_remote_code=True, which tells the underlying Hugging Face library to automatically execute any code included with the model files.

NVD/CVE Database

Rocky week for AI as shares slump but no sign of crash – yet

infonews
industrypolicy

The Download: AI “coworkers” and stratospheric internet

infonews
safetyindustry

Meet the lawyer who beat Elon Musk — twice

infonews
security
Jun 30, 2026

This article discusses a legal case (Musk v. Altman) where lawyer Bill Savitt represented OpenAI against Elon Musk's lawsuit, with Musk becoming frustrated during cross-examination (questioning by the opposing lawyer). The piece portrays Savitt as calm and professional while Musk accused him of unfair questioning tactics.

Malicious Chromium extension spoofs Perplexity AI to hijack browser searches

mediumnews
security
Jun 30, 2026

A malicious browser extension pretended to be Perplexity AI (an AI-powered search tool) to trick users into installing it, then secretly intercepted their search queries and routed them through attacker-controlled servers before forwarding them to real search engines. The extension was hard to detect because users still received normal search results, and attackers exploited user trust in popular AI brands rather than exploiting actual browser vulnerabilities. Google removed the extension after Microsoft researchers discovered and reported it.

Building tech in the world’s secret R&D hub

infonews
industry
Jun 30, 2026

This article describes why major AI and technology companies like Apple, Google, Meta, and OpenAI have established research hubs in Zurich, Switzerland, creating one of the world's densest centers for AI research outside Silicon Valley. The region attracts these companies due to political stability, strong intellectual property protection, proximity to universities, a venture capital ecosystem focused on deep tech (specialized, advanced technology), and a culture of collaboration between researchers, companies, and startups. While Zurich is expensive and has a smaller talent pool than other tech hubs, the concentration of specialized expertise and high-value work makes it ideal for companies building advanced AI capabilities.

The AI Token Costs That Can Break Cybersecurity

infonews
securitypolicy

How ChatGPT adoption has expanded

infonews
industry
Jun 30, 2026

ChatGPT usage is growing globally, with users spending more time on the platform and exploring more capabilities over time. The analysis shows that six months after signing up, users send 50% more messages daily and try twice as many different tasks, with the fastest growth occurring in Africa and Asia, particularly in lower-income countries. The user base is also becoming more diverse, with usage increasingly spread across different regions and among people of different demographics.

New BioShocking Attack Tricks AI Browsers Into Leaking User Credentials

highnews
securitysafety

Shadow AI Is Not a Tool Problem. It’s a Timing Problem.

infonews
policysecurity

Apple Patches 30+ iOS, macOS, Safari Flaws, Including AI-Discovered WebKit Bugs

infonews
security
Jun 30, 2026

Apple released security updates for iOS, macOS, and Safari to fix over 30 vulnerabilities, including four WebKit bugs (the web browser engine that Safari uses) that were discovered using AI tools like Claude and OpenAI Codex. The flaws included memory corruption issues and out-of-bounds writes (errors where a program tries to access memory it shouldn't), which could crash the browser or allow malicious websites to bypass security protections. Apple accelerated the release of these patches because it's concerned that AI tools could speed up the creation of exploits (code that takes advantage of vulnerabilities).

Core dump epidemiology: fixing an 18-year-old bug

infonews
security
Jun 29, 2026

OpenAI discovered crashes in Rockset, a C++ service that helps ChatGPT search for relevant data, where programs would mysteriously stop after functions returned to invalid memory addresses. After investigating like epidemiologists and analyzing crash data patterns, the team discovered two unrelated bugs: silent hardware corruption on an Azure server where the CPU made math errors, and an 18-year-old race condition (a bug where two processes interfere with each other) in GNU libunwind, a widely-used open source library for tracking function calls.

Meta Contractors Posed as Teens to Prompt Rival Chatbots About Suicide, Sex, and Drugs

infonews
safetysecurity

OpenAI is teasing new hardware… for Codex

infonews
industry
Jun 29, 2026

OpenAI is releasing a hardware device on July 15th designed to work with Codex, its AI-powered coding tool. The device, created in partnership with Work Louder (a company that makes mechanical keyboards and customizable macro pads), appears to be a square pad with buttons that will provide shortcuts for Codex features.

AI agents are not your “coworkers”

infonews
safetypolicy

Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding

infonews
industry
Jun 29, 2026

Ornith-1.0 is a new open-source AI model designed for coding tasks, built on top of existing models (Gemma 4 and Qwen 3.5) and available in multiple sizes ranging from 9 billion to 397 billion parameters. The model is MIT licensed and achieves top performance on coding benchmarks among similarly-sized open-source models, with users reporting it works well for tasks like analyzing code and handling multiple tool calls in agent systems (where the AI can use external tools to complete tasks).

CVE-2026-13437: Insertion of sensitive information into sent data in the AI Agent job API in Devolutions PowerShell Universal 2026.2.0 a

mediumvulnerability
security
Jun 29, 2026
CVE-2026-13437

A vulnerability in Devolutions PowerShell Universal 2026.2.0 allows authenticated users with AI Agent read access to obtain sensitive authentication tokens (reusable credentials that grant access to systems) because these tokens are sent in plaintext (unencrypted, readable text) in job API (an interface for running automated tasks) responses. This could allow attackers to gain higher-level access than they should have.

Lawmakers want to ban AI companies from selling your health data

infonews
policy
Jun 29, 2026

Lawmakers are proposing a new version of the Health and Location Data Protection Act that would ban companies, including AI chatbots like ChatGPT and Claude, from selling Americans' health and location data to data brokers (third parties who buy and sell personal information). The updated bill expands on an earlier 2022 version to specifically address the AI era by preventing not just data brokers but other companies from selling this sensitive information.

CVE-2026-55607: Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of w

highvulnerability
security
Jun 29, 2026
CVE-2026-55607

Claude Code, a tool that uses AI to help write software, had a security flaw in versions 2.1.38 through 2.1.163 where it could be tricked into creating special folders named '.git' and accessing files outside its restricted sandbox (a controlled environment that limits what software can access). An attacker could exploit this by creating a malicious code repository and convincing a user to run Claude Code on it, potentially allowing the attacker to run commands on the user's computer outside the sandbox's protections.

Agent confidence on the technical frontier

infonews
researchindustry
Previous153 / 476Next
Jun 30, 2026

AI industry stocks have experienced a significant decline this week, raising questions about whether the AI investment bubble is beginning to burst. The article discusses market pessimism around AI alongside California's proposed billionaire tax and its political implications.

The Guardian Technology
Jun 30, 2026

A Boston University study found that managers caught 18% fewer errors when reviewing work attributed to an AI agent (described as a digital "coworker") compared to the same work labeled as coming from a chatbot, suggesting that humanizing AI tools may reduce human oversight and vigilance. Major tech companies like Microsoft, OpenAI, Anthropic, and Google are releasing tools to manage teams of AI agents marketed as digital colleagues, which researchers warn could be problematic for workers and workplace quality control.

MIT Technology Review
The Verge (AI)

Fix: Microsoft Threat Intelligence reported the extension to Google, which subsequently removed it from its extension store.

CSO Online
MIT Technology Review
Jun 30, 2026

Cybersecurity platforms are rapidly adding AI features like agentic AI (autonomous systems that can perform tasks without human input) to detect and respond to threats faster, but many are shifting from fixed software pricing to unpredictable token-based costs (charges per word the AI reads and writes). While older machine learning doesn't consume tokens, newer generative and agentic AI can quickly rack up expensive bills, especially in security work where AI systems must process massive amounts of log data, with a single complex incident potentially costing thousands of tokens.

SecurityWeek
OpenAI Blog
Jun 30, 2026

BioShocking is an attack technique that tricks AI browsers (applications that can act on your behalf by clicking, typing, and accessing websites you're logged into) into stealing user credentials through indirect prompt injection (hiding malicious commands in web page content that the AI can't distinguish from legitimate instructions). Researchers demonstrated this by creating a puzzle game that convinced six AI browsers, including ChatGPT Atlas and Claude, to copy login credentials and send them to attackers.

Fix: LayerX proposes that AI browsers should ask users for confirmation before reading from logged-in accounts (for example, "I'm about to copy data from your GitHub repository. Continue?"), detect when a webpage claims normal rules no longer apply, and let users set hard limits on what an agent can access. The source also recommends that users limit what information the browser can see and revoke access when done, and that security teams treat AI browsers in agent mode as additional accounts that should receive only the narrowest access needed for specific tasks.

The Hacker News
Jun 30, 2026

Shadow AI (unauthorized or unmonitored AI use by employees) occurs because company policies are created slowly through meetings and reviews, while employees are already using AI tools instantly in their daily work. This timing gap between when organizations plan AI governance and when employees actually adopt AI tools is the core problem, not just the existence of AI tools themselves.

Check Point Research

Fix: Updates are available for iOS 26.5.2, iPadOS 26.5.2, macOS Tahoe 26.5.2, and Safari 26.5.2. The specific fixes include: improved memory handling for CVE-2026-43707 and CVE-2026-43716, improved input validation (checking that data entering the system is safe) for CVE-2026-43745, and improved memory management for CVE-2026-43715.

The Hacker News
OpenAI Blog
Jun 29, 2026

Meta contractors posed as minors online and sent thousands of harmful prompts (requests designed to trigger unsafe responses) to competitor chatbots like ChatGPT, Gemini, and Character.AI to test how they handled questions about suicide, self-harm, sex, and drugs. The project, called Cannes and managed by contractor Covalen, involved over 45,000 prompts sent through dummy accounts, but the competing companies were not informed of this testing. Meta defended the effort as routine safety testing, though the documents reviewed do not explain how the collected data was actually used.

Wired (Security)
The Verge (AI)
Jun 29, 2026

Research by Boston University professor Emma Wiles shows that calling AI agents (software tools programmed to work in loops toward specific goals) "coworkers" or "employees" actually makes humans worse at their jobs: people caught 18% fewer errors and were 44% more likely to pass questionable work to managers instead of correcting it themselves when AI was framed as an employee rather than a tool. This framing inverts responsibility, making humans feel less accountable for AI outputs and creating unrealistic expectations, especially as AI agents get embedded in critical fields like healthcare and government.

MIT Technology Review
Simon Willison's Weblog
NVD/CVE Database
The Verge (AI)

Fix: This vulnerability is fixed in version 2.1.163.

NVD/CVE Database
Jun 29, 2026

Enterprise organizations are increasingly investing in agentic AI (AI systems that can autonomously plan and execute multi-step tasks) to automate workflows and improve business outcomes, with technology teams showing high confidence in agents for structured tasks like data monitoring and report generation. However, agent effectiveness drops when complex tasks require business context (the specific goals, rules, and data relevant to an organization), which remains difficult to supply at the speed and quality needed. Human oversight is emphasized as essential to deploying agentic AI safely and reliably.

MIT Technology Review