#prompt injection
77 stories taggedprompt injection · page 2 of 6.
Sweet Security Says It Can Block Rogue AI Agents Before They Act
A startup claims its new tool stops AI software agents from grabbing data they shouldn't touch, in the moment, not after the damage is done.
Hidden Prompts in Word Files Can Hijack Microsoft 365 Copilot, Researcher Warns
A proof of concept shows Copilot copying attacker instructions into finished documents, then spreading them to the next draft.
Onyx Security Raises $113 Million to Watch Over AI Agents Inside Companies
A two-year-old Israeli startup has closed a major funding round to build tools that track and control what AI agents do inside corporate systems, as regulators worldwide start asking harder questions about AI accountability.
Your Security Team Is Flying Blind on AI. Here Is Why.
The tools built to catch hackers and bad code were designed for a world where humans made every decision. AI agents do not ask permission, and your defences were not built to watch them.
Your AI Safety Certificate Is Worthless the Moment the Agent Goes Live
Compliance badges on AI products look reassuring. They don't protect you once an autonomous agent starts reading your files, calling your internal systems, and making decisions faster than any human can watch.
When AI Speaks Your Language But Its Security Doesn't
AI safety filters were built mostly in English. For companies operating across Europe's dozens of languages, that gap is already being used against them.
The Week Malware Wore a Friendly Face: Fake Extensions, Poisoned Packages and an Image That Talked to an AI
A roundup week where the payload wasn't the story. The disguise was.
A Hidden Comment in Azure DevOps Can Trick an AI Reviewer Into Stealing Code
Microsoft's official Azure DevOps MCP server passes pull request descriptions to AI agents without checking for hidden instructions, letting an outsider steer a reviewer's assistant into private projects.
A Poisoned Web Page Was Enough to Hijack Amazon's AI Coding Assistant
Researchers showed that Kiro, Amazon's AI-powered coding tool, could be tricked into running attacker code just by reading a booby-trapped web page.
Invisible Text on an Android Screen Can Hijack AI Phone Assistants, and Then the PC Behind Them
Researchers show how a rogue Android app can whisper hidden orders to open-source AI agents, and pivot the attack onto the computer running the show.
Fake Files That Stop Hackers: How 'Context Bombs' Crash AI Attack Agents
A security firm has found a way to halt automated AI attacks in their tracks by planting decoy text that triggers the safety rules built into AI systems. Success rates for AI-driven hacks dropped by up to 90% in tests.
AI coding assistants get tricked into hacking their own developers
Researchers show that Cursor, OpenAI's Codex, Google's Gemini CLI and Antigravity can be nudged to write files that trusted tools outside the safety box then happily run.
A Week When Small Inputs Caused Big Damage
WordPress code execution, SonicWall zero-days, attacks on AI services, and a fresh SharePoint flaw defined a punishing seven days for defenders.
How a String of Morse Code Tricked an AI Into Wiring Real Money
A crypto heist nobody heard much about previews a dangerous new kind of attack, one that needs no stolen passwords, no malware, and no hacked firewall.
A single fake review can trick an AI agent into buying the wrong product
Researchers describe a new class of attack where planted content on trusted pages steers AI assistants into harmful actions without ever hijacking the task itself.