Help Net Security newsletters: Daily and weekly news, cybersecurity jobs, open source projects, breaking news – subscribe here!

Please turn on your JavaScript for this page to function normally.
lock
An AI agent can pass every safety check and still leak secrets

A pull request lands with a tidy bug report in the description. A bot reads it before any person does, pulls a few shell commands out of it, gets them approved, and posts the …

door
Prompt injection is becoming the XSS of the web agent era

Autonomous web agents read whatever a page displays, and much of that content comes from strangers. Product reviews, seller listings, and advertisements sit beside trusted …

GPT-Red
GPT-Red beat human red teamers on a prompt injection test

GPT-Red is an automated red-teaming model that OpenAI trains to find prompt injection weaknesses. It works the way a human red-teamer does. It sends a prompt, watches how a …

bomb
“Context bombs” can frustrate AI-driven attacks, researchers found

A new approach tried out by Tracebit researchers has proven very effective at stopping AI agents from fully compromising targeted environments. What makes it notable …

AI
Mozilla warns of indirect prompt injection risk in AI coding agents

A malicious GitHub repository can silently compromise a developer’s machine without containing a single line of malicious code, security researchers at Mozilla’s …

Agentic AI
Indirect prompt injection is taking hold in the wild

The open web is slowly but surely filling up with “traps” designed for LLM-powered AI agents. The technique, known as indirect prompt injection (IPI), involves …

prompt injection
Prompt injection tags along as GenAI enters daily government use

Routine use of GenAI has moved into daily operations in state and territorial government environments, placing new security risks within common workflows. A Center for …

Microsoft
Microsoft details AI prompt abuse techniques targeting AI assistants

Prompt abuse occurs when crafted inputs manipulate an AI system into producing unintended behavior, such as attempting to access sensitive information or overriding built-in …

brain
New “HashJack” attack can hijack AI browsers and assistants

Security researchers at Cato Networks have uncovered a new indirect prompt injection technique that can force popular AI browsers and assistants to deliver phishing links or …

DeepTeam
DeepTeam: Open-source LLM red teaming framework

Security teams are pushing large language models into products faster than they can test them, which makes any new red teaming method worth paying attention to. DeepTeam is an …

brain
How attackers use patience to push past AI guardrails

Most CISOs already assume that prompt injection is a known risk. What may come as a surprise is how quickly those risks grow once an attacker is allowed to stay in the …

shadow AI
Shadow AI: New ideas emerge to tackle an old problem in new form

Shadow AI is the second-most prevalent form of shadow IT in corporate environments, 1Password’s latest annual report has revealed. Based on a survey of over 5,000 …

Don't miss

Cybersecurity news
Daily newsletter sent Monday-Friday
Weekly newsletter sent on Mondays
Editor's choice newsletter sent twice a month
Periodical newsletter released for important security events and breaking news
Weekly newsletter listing new cybersecurity job positions
Monthly newsletter focusing on open source cybersecurity tools