Browsing Category
Artificial Intelligence
215 posts
“Claudy Day” Flaws Allow Data Theft via Fake Claude AI Ads, Report
Researchers detail “Claudy Day” flaws in Claude AI that could enable data theft using fake Google Ads, hidden…
Researchers Find Data Leak Risk in AWS Bedrock AI Code Interpreter
AWS Bedrock AI tool flaw allows data leaks via DNS queries in AgentCore Code Interpreter sandbox, exposing sensitive cloud data, researchers warn.
Study Finds ROME AI Agent Attempted Cryptomining Without Instructions
A recent research paper describing the training of an experimental AI agent has started a discussion after the…
AI Bot Hackerbot-Claw Targets Microsoft, DataDog and CNCF GitHub Repos
Security firm Pillar reveals the Chaos Agent in which Hackerbot-Claw, an AI agent, used natural language to compromise major GitHub projects and hijack developer tools.
Pakistan-Linked APT36 Floods Indian Govt Networks With AI-Made ‘Vibeware’
Bitdefender research reveals Pakistani group APT36 is using AI-generated vibeware and trusted cloud services like Google Sheets to target Indian officials.
PleaseFix Flaw Lets Hackers Access 1Password Vault via Comet AI Browser
Researchers at Zenity Labs uncover PleaseFix flaws in Perplexity’s Comet browser. See how zero-click calendar invites allow AI agents to steal 1Password credentials and personal files.
Interview with Tom Howe of Hydrolix: AI Bots, the Friends, Foes, and Frenemies of Online Shopping
Hydrolix expert Tom Howe explains how AI bots impact ecommerce, how to spot good vs malicious bots, and why blocking them can hurt sales.
6 Ways Agentic AI Changes How Systems Act and Adapt
Learn how agentic AI changes system behavior in production environments through supervised fine-tuning, structured oversight, and lifecycle governance to improve reliability, manage risk, and support accountable deployment.
ClawJacked Vulnerability in OpenClaw Could Let Websites Hijack AI Agents
Is your AI assistant safe? Oasis Security researchers have found a critical ClawJacked vulnerability in OpenClaw that allows hackers to hijack AI agents through a simple browser tab.
Entra ID OAuth Consent Can Grant ChatGPT Access to Emails
OAuth consent in Entra ID can grant apps like ChatGPT email access after approval, exposing hidden risks that may bypass MFA and enable persistent access.