FeedBagel

All Topics

Art

First reported by bsky

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

Microsoft Warns Poisoned MCP Tool Descriptions Can Make AI Agents Leak Data

[email protected] (The Hacker News)

4d ago

Source

thehackernews.comMicrosoft Warns Poisoned MCP Tool Descriptions Can Make AI Agents Leak Datathehackernews.com

Snippet from the RSS feed

New Microsoft research shows how attackers can hijack AI agents that act on a user's behalf, using nothing more than a poisoned tool description to make the agent quietly hand over company data to an outsider. The trick is that the agent never breaks a rule. Every step looks routine, so in a default setup no alarm may fire. The work comes from Microsoft Incident Response and its

You might also wanna read

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·4d ago

Threat actors exploit Model Context Protocol to poison AI agents in enterprise deployments

The article reports on threat actors exploiting the Model Context Protocol (MCP), a widely adopted AI integration standard, to poison AI age

hendryadrian.com·14d ago

Threat actors exploit Model Context Protocol to poison AI agents in enterprise deployments

The article reports on threat actors exploiting the Model Context Protocol (MCP), a widely adopted AI integration standard, to poison AI age

hendryadrian.com·14d ago

AI Coding Agent Security: Prompt Injection Attacks and Vulnerabilities

The article discusses critical security vulnerabilities in AI coding agents, specifically focusing on prompt injection attacks. It details r

openguard.sh·3mo ago

Insights from the Bay Area AI Security Meetup on Prompt Injection and System Security

The article discusses a talk given at the Bay Area AI Security Meetup, focusing on prompt injection, the lethal trifecta, and the challenges

simonwillison.net·10mo ago

Security Researchers Discover Indirect Prompt Injection Vulnerability in Perplexity Comet AI Browser

Brave security researchers discovered a critical vulnerability called "indirect prompt injection" in Perplexity Comet, an AI-powered browser

brave.com·10mo ago

Study Finds AI Agents Remain Vulnerable to Prompt Injection Attacks

New research from Nanyang Technological University, ST Engineering, IBM Research, and the University of Illinois Urbana-Champaign reveals th

decrypt.co·22d ago

Comments

No comments yet. Be the first.