Smart Adblocker Chrome Extension Steals AI Chatbot Conversations
Smart Adblocker is a malicious Chrome extension with 90,000 users that poses as an ad blocker but captures and exfiltrates AI chatbot…
Tag: AI Security
Orphaned AI Agents: Uncovering Hidden Access Risks in Your Network
The rapid adoption of internal AI tools has created a significant security blind spot: orphaned AI agents. These are automated tools left…
Webinar: Orphaned Agents & Standing Privileges
A technical webinar hosted by The Hacker News and SailPoint focusing on the hidden access risks of internal AI, including orphaned agents…
Token Security: AI-First Security for AI Agents
Token Security is an AI-first security company that helps organizations discover, understand, and enforce what AI agents can do across every platform.…
Legacy Infrastructure Exposures Enable AI Agent Hijacking, Warns XM Cyber
At the Gartner Security & Risk Management Summit, Zur Ulianitzky, SVP Product and Security Research at XM Cyber, detailed how attackers are…
DifyTap Vulnerabilities Expose AI Chat Data Across Tenants in Open-Source Platform Dify
Cybersecurity researchers at Zafran Security have disclosed four vulnerabilities in Dify, an open-source agentic workflow platform with over 146,000 GitHub stars, collectively…
Claude Code Resists GhostSplice in Tests
GPT-5.4 dropped to 0% compliance behind Claude Code, suggesting that Claude Code's safety controls may mitigate the GhostSplice attack.
Agentic AI: The Weapon That No Longer Needs a Warrior
Agentic AI represents a paradigm shift in offensive cybersecurity, where AI tools no longer require human operators to execute attacks. Unlike previous…
Novee Security Uncovers AI Agent Harness Flaws
Novee Security is the research firm that discovered the vulnerabilities in Claude Code, Gemini CLI, and Codex. They presented their findings at…