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 ...
Hackaday

Chain-of-Thought Spoofing Targets Reasoning AI Models

Menell] have shown that AI Large Language Models (LLMs) can fail to correctly distinguish between different instruction ...

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 ...

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 ...
Dark Reading

ChatGPT's Memory Feature Supercharges Prompt Injection

Some of the latest, best features of ChatGPT can be twisted to make indirect prompt injection (IPI) attacks more severe than they ever were before. That's according to researchers from Radware, who ...
CSO Online

M365 Copilot SearchLeak: Your prompt injection attack surface just got bigger

Although not the first of its kind, researchers’ POC attack against Microsoft’s M365 Copilot Enterprise underscores parameter ...
Forbes

When AI Agents Turn Against You: The Prompt Injection Threat Every Business Leader Must Understand

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. Prompt injection attacks can manipulate AI behavior in ways that traditional cybersecurity ...
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) ...
VentureBeat

Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for

Run a prompt injection attack against Claude Opus 4.6 in a constrained coding environment, and it fails every time, 0% success rate across 200 attempts, no safeguards needed. Move that same attack to ...
9to5Mac

Researchers detail how a prompt injection attack bypassed Apple Intelligence protections

A now corrected issue allowed researchers to circumvent Apple’s restrictions and force the on-device LLM to execute attacker-controlled actions. Here’s how they did it. Interestingly, they ...
Unite.AI

DeepKeep Uncovers ‘InkJect,’ a New AI Attack That Hides Malicious Prompts Inside Images

As enterprises rapidly embrace multimodal AI capable of understanding both text and images, security researchers are discovering that these powerful new capabilities introduce equally sophisticated ...