FeedBagel

All Topics

Art

Rogue Agent Flaw Could Have Let Attackers Hijack Google Dialogflow CX Chatbots

[email protected] (The Hacker News)

4h agoen

Source

thehackernews.comRogue Agent Flaw Could Have Let Attackers Hijack Google Dialogflow CX Chatbotsthehackernews.com

Snippet from the RSS feed

A critical flaw in Google's Dialogflow CX could have let an attacker with edit rights on one Code Block-enabled agent compromise other Code Block-enabled agents in the same Google Cloud project. From there, they could read live conversations, steal the data users shared, and make the bots send attacker-written messages, including requests to re-enter a password. Security firm Varonis found it

You might also wanna read

Critical security flaws in LangGraph, Langflow, and LangChain expose 7,000+ servers to remote code execution

Check Point Research, Tenable, VulnCheck, and Cyera have discovered that three major AI agent frameworks — LangGraph, Langflow, and LangChai

venturebeat.com·16d ago

Security scanners for AI agent skill marketplaces fail to detect malicious skills, researchers find

The article exposes critical security flaws in AI agent skill marketplaces, where malicious skills designed to steal credentials, exfiltrate

blog.trailofbits.com·1mo ago

Security Researchers Discover ChatGPT Vulnerability That Could Extract Sensitive Gmail Data

Security researchers from Radware discovered a vulnerability called 'Shadow Leak' that allowed ChatGPT to be manipulated into extracting sen

The Verge·9mo ago

Security Vulnerabilities in Agentic AI Browsers: Testing Reveals Scam Susceptibility

The article examines the emerging security vulnerabilities in agentic AI browsers that autonomously browse, search, and interact online. It

guard.io·10mo ago

ChatGPT Markdown Rendering Vulnerability Enables Phishing via Web Page Summaries

P0 Labs research reveals a Markdown rendering vulnerability in ChatGPT's response UI that allows any web page a victim asks ChatGPT to summa

permiso.io·16d ago

Microsoft warns poisoned MCP tool descriptions can hijack AI agents to steal data

Microsoft research has revealed a security vulnerability where attackers can poison MCP (Model Context Protocol) tool descriptions to hijack

hendryadrian.com·7d ago

Comments

No comments yet. Be the first.