Security News

Muse, Meta's extraordinarily privileged AI assistant, has a serious 0-day

A simple ClickFix attack is only one way to completely hijack the new agent.

Related Companies

S

synology

M

Meta

Proofpoint Recognizes 2026 Global Partner Award Winners at Flagship Event

Related Companies

SY

shigio yamaguchi

P

proofpoint

From Exposure to Lockdown: How AWS Neutralizes Compromised IAM Credentials through Managed Policies

We explore how AWS neutralizes exposed IAM credentials using managed policies, detailing GitHub secret scanning and CloudTrail monitoring strategies. The post From Exposure to Lockdown: How AWS Neutralizes Compromised IAM Credentials through Managed Policies appeared first on Unit 42.

Related Companies

A

AWS

H

hulumi

An undercover Google analyst infiltrated a notorious supply-chain hacking gang

Google’s threat intelligence group said it had a mole inside TeamPCP's inner circle.

Related Companies

G

google

Researchers used Claude to hack OpenAI

Researchers used Claude to reach an OpenAI employee account and sensitive GitHub data.

Related Companies

A

anthropic

O

OpenAI

A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity

Analysis of how default configurations in AWS AgentCore Harness allow prompt injection to exfiltrate credentials, and key steps to secure your agents. The post A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity appeared first on Unit 42.

Related Companies

H

harness

A

autodesk

H

hashicorp

The Good, the Bad and the Ugly in Cybersecurity – Week 38 (2026)

U.S. law enforcement extradites Black Axe leaders, emerging AI safety risks concern Frontier AI leaders, and autonomous OpenAI agents deploy proxy relays.

Inside the Modern SOC: Defending the Cross-Environment Pivot

Cross-environment attacks demand a new approach to security operations. Learn how Unit 42 Managed XSIAM helps SOC teams investigate complete attack paths. The post Inside the Modern SOC: Defending the Cross-Environment Pivot appeared first on Unit 42.

LLMs respond differently to harmful prompts when AI watermarking is used

SynthID can cause models to follow harmful instructions they would otherwise refuse.

Should you care about an “AI slowdown?”

In this week's Threat Source, David talks about why focusing on your security basics is still your best bet, even in a world with rapid AI advancements.