CISOs need to prepare for a vulnerability discovery onslaught, even as attackers will still have work to do to operationalize ...

Tuesday, Databricks rolled out Genie One, an AI "agentic coworker" that plugs straight into a company's live data and ...

Look to these key metrics and benchmarks to evaluate the performance, capability, reliability, and safety of your AI models ...

Prompt injection is the technique of smuggling instructions to an AI agent through content the agent reads — a document, a calendar invite, a web page, a code comment — so that hostile text carries ...

Welcome to Saturday Hashtag, a weekly place for broader context. Saturday Hashtag: #AIPoisonPill originally appeared on ...

Three patched LangGraph flaws could let attackers chain SQL injection and unsafe deserialization for RCE in self-hosted ...

Attackers are exploiting three Fortinet FortiSandbox flaws, including one patched last week, risking auth bypass and command ...

A recent Microsoft Copilot exploit demonstrates how AI can make existing cybersecurity bugs even more virulent.

A new benchmark study found AI agents remain vulnerable to prompt injection attacks as companies increasingly roll out the ...

CVE-2026-10520, a critical-severity vulnerability in Ivanti Sentry, was flagged as exploited based on activity observed on ...

Our tracking of OceanLotus activities from 2024–2026 reveals a shift in operational focus. During this period, the Vietnam-aligned OceanLotus adopted a more selective approach to external operations ...

Varonis found a way to chain three bugs into one exploit that can lead to data exfiltration.