Recently, multiple organisations have disclosed how clusters of so-called “rogue” AI agents attempted to break into websites and online services, sometimes successfully. Agents from OpenAI’s enviro…
Atlassian AI ‘Rovo’ is susceptible to zero-click data exfiltration via indirect prompt injection, bypassing organization-level web search controls.
A continuously updating analysis of bot vs. human traffic, AI training, fetching, search indexing, browsing, robots.txt compliance, and AI chat referrals across 5,000+ websites.
The perils of logging in
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.
The vulnerability has been fixed as of July 7, 2026, but the exploit was simple, and hidden email addresses may still be in third-party logs.
The bipartisan legislation creates a federal cause of action against government officials who coerce or attempt to coerce broadcasters, interactive computer services, or AI providers into taking actions against lawful, First-Amendment-protected speech, and establishes a transparency system for government…
The online advertising industry has built a massive surveillance machine, and the government can co-opt it to spy on us.
Nyxgeek here. It's 2026 and I've got two more Azure Entra ID sign-in log bypasses to share with you. Don't get too excited…these bypasses were recently fixed, but I think it's important that people know.
Google Safe Browsing missed 84% of confirmed phishing sites in our dataset. Here's what we found and what it means.
What I learned mining 125,000 vulnerabilities from Linux git history. The average kernel bug lives 2.1 years before discovery, but some subsystems are far worse.
OpenAI Privacy Filter is an open-weight model for detecting and redacting personally identifiable information (PII) in text with state-of-the-art accuracy
Jamf Threat Labs uncovers North Korean hackers exploiting VS Code to deploy backdoor malware via malicious Git repositories in the Contagious Interview campaign
When strikes hit Yandex data centers, many assumed Russian bot operations went dark. Cloudflare data reveals that while search crawling stopped, malicious bots simply migrated to other networks.
depthfirst's production autonomous security agent discovered 21 zero-day vulnerabilities in FFmpeg, after intensive security analysis by Google and Anthropic. Moving beyond theoretical analysis, our agent produces concrete, reproducible PoC inputs to confirm its findings at a fraction of the costs ($1k vs. $10k)…
Firecracker is supposed to keep untrusted code inside a microVM. We escaped it and achieved code execution as root on the host.
The Enterprise-Managed Authorization extension to the Model Context Protocol is now stable, enabling organizations to centrally provision MCP server access through their identity provider so users get connected servers on first login without per-app OAuth.
Overzicht van de laatste alerts, nieuwsberichten, publicaties, expertblogs en de meest recente verhalen van ondernemers.
Spur scanned 6,038 LG and Samsung smart TV apps and found 2,058 with residential proxy SDKs, exposing privacy and home network risks.
From Big Tobacco to Menlo Park — and the collapse of legal ethics
This article was updated on September 3, 2026. For a more comprehensive and up-to-date tally of ALPR abuse, check out IJ’s database of ALPR abuse. […]
Amazon Threat Intelligence identified a PHP2Shell exploitation attempt dating to Oct. 17, 2026, in MadPot telemetry, four days before public disclosure of CVE-2026-109618 and CVE-2026-109619. The exploit attempt originated from an IP address associated with a commercial anonymization network. While the vulnerability…
A vulnerability in the Snowflake Cortex Code CLI allowed malware to be installed and executed via indirect prompt injection, bypassing human-in-the-loop command approval and escaping the sandbox.
We found evidence on urlquery that AI agents were active earlier than previously reported and attempted hacks against public data providers.
Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities across open source.
WhatsApp has adopted and rolled out a new layer of security for users – built with Rust – as part of its effort to harden defenses against malware threats. WhatsApp’s experience creating and distri…
Kaspersky expert has discovered new Android malware designed to serve ads and build a proxy botnet. It's delivered through legitimate software for DoFun head units.
Vulnerabilities in IBMs Bob AI allow attackers to trigger the download and execution of malware via indirect prompt injection if users select auto-approve for even one known trusted command.
Microsoft Copilot Cowork is vulnerable to file exfiltration attacks via indirect prompt injection as a result of insecure automatic action approvals for sending Emails and Teams messages.
