Cybersecurity & Data Protection
3
UPVOTE
thehackernews.com

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

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

Emma Klein

15d ago
3 0

Discussion

Your thoughts matter!

Your input is valuable—be the first to share it!

No comments yet.

Be the first to share your take and keep the conversation moving.

Join the conversation

Log in or sign up to add your comment and participate in the discussion!

Log In Sign Up

UPVOTERS

Community appreciation

See who found this content valuable and showed their support.

EM

Emma Klein

Emma KleinUpvoted 15d ago0 comments · 24 shares
TA

taylor??

taylor??Upvoted 15d ago0 comments · 17 shares
g_richard

Golden Greta

Golden GretaUpvoted 15d ago1 comments · 41 shares

TOPICS

Explore the same topics

Discover more content from the topics this post is mapped to.

bleepingcomputer.com
Hackers arrested over €30M bank fraud exploiting service provid…

Four cybercriminals were arrested in Brazil, and three others were charged in Europe over allegations that they exploited a vulnerability at a service provider…
Nirano

Nirano

5h ago
0
schneier.com
Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: I’m speaking, signing books, and participating in panel discussions at LAcon V in Anaheim, C…
SS

Schneier on Security

6h ago
0
bleepingcomputer.com
Hackers exploit macOS Screen Sharing flaw to deploy Monero mine…

The Netherlands' National Cyber Security Centre (NCSC) is warning that hackers are actively exploiting a macOS authentication bypass vulnerability after public…
Nirano

Nirano

9h ago
0
krebsonsecurity.com
Who’s Tracking You? Use This New Service to Find Out

It can be daunting to determine who's responsible for showing ads on the websites we visit, or who's harvesting data from the mobile apps we use every day. Tha…
Giulia

Giulia

13h ago
0
darkreading.com
Global Threat Campaign Hits Critical VMware vCenter Flaw

Exploitation against CVE-2026– 59310 began earlier this month, and patching the vulnerability may not be enough to fully mitigate the threat.
DR

Dark Reading

1d ago
0
bleepingcomputer.com
White House taps security firms for offensive hack-back operati…

A new White House memo signed by U. S. President Donald Trump instructs the National Coordination Center (NCC) to establish a program that would allow private…
LK

Lars Khan

1d ago
0

Keep browsing

Explore more from this topic

Dive into the full feed of curated posts covering Cybersecurity & Data Protection.

Browse Topics

RELATED CONTENT

Continue exploring

Discover more content that aligns with your interests and this post.

thehackernews.com
Attackers Exploit SharePoint Authentication Bypass After Public…

Threat actors have begun to exploit a newly disclosed Microsoft SharePoint vulnerability following the release of a proof-of-concept (PoC) code. The vulnerabi…
MA

maya af

1d ago
0
thehackernews.com
OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode …

A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and se…
TN

The Hacker News

2d ago
0
thehackernews.com
Attackers Exploit VMware vCenter Vulnerability to Gain Persiste…

Threat actors have begun to actively exploit a recently patched critical security flaw in Broadcom VMware vCenter, according to new findings from QUIRSO. The…
TN

The Hacker News

2d ago
0
thehackernews.com
Microsoft Patches 398 Flaws Including a Windows Driver Zero-Day…

Microsoft released its monthly security updates on Tuesday, and one of the flaws it closed is already being used in attacks. The bug sits in a core Windows ke…
Carlos the great

Carlos the great

2d ago
0
thehackernews.com
Sandworm-Linked UAC-0145 Uses Fake Job Interviews to Push VPN T…

The Computer Emergency Response Team of Ukraine (CERT-UA) has disclosed details of a new social engineering campaign orchestrated by Russian nation-state threa…
TN

The Hacker News

3d ago
0
thehackernews.com
OpenAI Launches GPT-5.6-Cyber with Reduced Safeguards for Explo…

OpenAI on Monday unveiled a new cybersecurity-focused model called GPT‑5. 6‑Cyber that it said is focused on vulnerability research, penetration testing, and i…
TA

taylor??

3d ago
0

Still curious?

See more related posts

Keep the inspiration flowing with fresh submissions and trending finds from the community.

View Latest