Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers

In 2025 and 2026, several independent sources have highlighted the same trend: Prompt injection remains one of the most ...
Decrypt

AI Researchers Got Chatbots to Share Cocaine Recipes Using This One Wild Trick

Researchers say a new jailbreak technique tricked AI models into treating attacker-written text as their own reasoning, ...

Prompts Are The New Malware As Enterprise AI Defenses Fall Behind

CrowdStrike data and OpenAI's admission confirm prompt injection as a dominant enterprise AI attack vector. 65% of ...

North Korea-Linked macOS Malware Uses Prompt Injection to Evade AI Analysis

SentinelOne says macOS.Gaslight uses prompt injection to mislead AI-based malware analysis, steal data, and use Telegram for ...

Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection

The authors developed an attack called CoT (Chain of Thought) Forgery that involves using an LLM to spoof the terse style of ...
CSO Online

Sandbox bypass flaws in Cursor IDE highlight prompt injection as an RCE vector

Researchers have discovered two vulnerabilities in the widely used Cursor AI-enabled integrated development environment (IDE) ...

This macOS malware can avoid AI analysis with gaslighting prompts hidden inside its architecture

A new piece of malware tries to trick AI-assisted analysis into showing errors.

Prompt injection to deepfakes: How AI rewrites rules of enterprise security

From AI agents and deepfakes to prompt injection, cybersecurity teams are confronting risks that traditional defences were ...
The Hacker News

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis

SentinelOne details Gaslight, a Rust-based macOS implant linked to North Korea-aligned actors that uses prompt injection to ...
Hosted on MSN

Hackers can use prompt injection attacks to hijack your AI chats — here's how to avoid this serious security flaw

While more and more people are using AI for a variety of purposes, threat actors have already found security flaws that can turn your helpful assistant into their partner in crime without you even ...
InfoQ

Prompt Injection for Large Language Models

Your LLM-based systems are at risk of being attacked to access business data, gain personal advantage, or exploit tools to the same ends. Everything you put in the system prompt is public data.