Prompt Injections for Defense
Prompt Injections for Defense This seems to work: Researchers from Tracebit on Monday said they found that placing prompt injections...
Prompt Injection
Claude Code Espionage Campaign Exposes a New Enterprise AI Risk
In September 2025, Anthropic detected suspicious activity in its Claude Code tool, which turned out to be a state-sponsored espionage...
New BioShocking Attack Tricks AI Browsers Into Leaking Credentials
AI browsers promise to help users get things done faster. BioShocking shows how the same convenience can lead to a...
North Korea-Linked macOS Malware Uses Prompt Injection to Evade AI Analysis
Malware has learned a new trick: manipulating the AI tools security researchers increasingly rely on to understand it. SentinelOne researchers...
Five Eyes Warns AI Could Speed Cyberattacks Within Months
Cyber agencies from the Five Eyes intelligence-sharing alliance — Australia, Canada, New Zealand, the UK, and the US — warned...
OpenAI Expands ChatGPT Lockdown Mode to Millions of Eligible Users
ChatGPT’s stricter security mode is getting a wider release. OpenAI is making Lockdown Mode, an optional setting in ChatGPT that...
Gartner SRM 2026 Signals a Cybersecurity Shift From Prevention to Resilience
The old success metrics no longer survive contact with reality. There is a particular kind of clarity that comes from...
Malicious WhatsApp, Slack Alerts Could Have Exposed Millions of Android Users
A routine phone notification could have become an attack path for Google Gemini on Android, according to new research from...
The Next AI Security Failure May Start With a Trusted Assistant
An AI assistant does not need to “go rogue” to create a security incident. It only needs to follow the...
AWS Rex Is a Big Step for Agentic AI Security, But Not the Final Layer
AWS Rex adds runtime guardrails for agentic AI, but security leaders still need data-layer controls to satisfy compliance and audit...
Indirect Prompt Injection Is Now a Real-World AI Security Threat
Last week, researchers at Google and Forcepoint reported that indirect prompt injection — a category of attack the security community...
GrafanaGhost: The AI That Leaked Everything Without Being Hacked
Image: Prostock-studio/Adobe No credentials were stolen. No alerts were triggered. And yet, the data slipped out anyway. On April 7,...
The Arms Race is Already Over. You Just Don’t Know Which Side Won.
Anthropic recently announced that Claude Opus 4.6 autonomously discovered more than 500 zero-day vulnerabilities in open-source software, including libraries...
The Next Billion Users Won’t Be Human: Securing the Agentic Enterprise
image: envato by Rawpixel For decades, the “user” at the heart of enterprise security has been a person. We built...
Which Came First: The System Prompt, or the RCE?
During a recent penetration test, we came across an AI-powered desktop application that acted as a bridge between Claude...
