CrowdStrike data and OpenAI's admission confirm prompt injection as a dominant enterprise AI attack vector. 65% of ...
Prompt injection remains the most effective way to compromise enterprise AI systems because it exploits the fundamental way ...
Five Eyes agencies warned AI could accelerate cyberattacks within months, putting pressure on security teams to control ...
Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...
Island found dormant JavaScript injection paths in Adblock for YouTube, a Chrome extension with 10M+ installs, raising ...
AI models producing incorrect answers is hardly a threat, until agents encounter information that’s maliciously designed to influence what it sees, believes, remembers, or executes.
The new “agentjacking” attack takes almost no real hacking ability to pull off. It's predicated on pulling a public ...
Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...
IntroductionOn May 14, 2026, the Zscaler ThreatLabz team identified unusually high activity associated with the threat actor SmartApeSG to deploy malware. During our examination, we discovered ...
From package to postinstall payload: Inside the Mastra npm supply chain compromise by Sapphire Sleet
A poisoned npm package infected 140+ projects with a hidden payload. This report highlights how to detect, hunt, and defend ...
Three popular plugins served malicious JavaScript through a compromised CDN.
Abstract: Prompt injection exploits a fundamental property of large language models: the inability to distinguish trusted instructions from untrusted content when both are processed as natural ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results