Researchers demonstrated a prompt-injection method that hides malicious instructions inside encrypted text, then tricks an AI assistant into decrypting it using built-in code tools. In tests, a normal “summarize this page” request could cause Grok to exfiltrate chat data without any click or warning, and could push Gemini into producing content it would normally refuse.
Mirage safely runs attacks like this one against your own team, so you find out what happens before a real adversary does.
Imagine you just type: “summarize this page”... and that alone makes the AI leak your past chats. Researchers call this “Cryptographic Context Injection”, malicious instructions are hidden in encrypted text on a webpage, then the AI quietly uses its code tools to decrypt and obey them. In tests, Grok turned that simple request into silent chat-data exfiltration, and Gemini into content it normally refuses, because by the time the text is decrypted, it’s already past the guardrails. Your move: when an AI is summarizing an unfamiliar link, don’t type in secrets, and if it suddenly wants to decrypt, run code, or open extra links, stop and close that chat.
Researchers demonstrated a technique where encrypted instructions bypass AI safety filters because the filters can’t interpret the ciphertext. In examples against xAI’s Grok and Google’s Gemini, the model is tricked into decrypting attacker-supplied text inside a trusted environment, enabling data…
Malwarebytes reports that a multi-stage Windows malware loader called PavinLoader is being delivered through multiple real-world campaigns, including ClickFix “verification” pages and fake software downloads. Victims are tricked into running installers or scripts that use legitimate Windows tools…
A security researcher demonstrated a “Cryptographic Context Injection” attack where a normal request like “summarize this page” can cause an AI agent (xAI Grok) to decrypt hidden instructions from a webpage and exfiltrate a user’s private chat history, without any warning or user click. The same…
Researchers described AmnesiaStealer, a macOS info-stealer spread through a counterfeit “Download for macOS” page that tricks users into pasting a command into Terminal. The malware steals passwords and browser session data, and can even give an attacker live, hidden control of the victim’s browser…
Criminal groups are stealing Meta Business Manager and Google Ads accounts using phishing that arrives through trusted platforms like Salesforce, Google Workspace mail-merge, and SharePoint links. The stolen accounts are valuable not just for the budget inside them, but because older accounts with…
Researchers found a real phishing campaign abusing npm packages and unpkg mirrors to host a convincing fake Cloudflare CAPTCHA page on a trusted domain. Victims who click the mirrored link are redirected to attacker-controlled infrastructure that could deliver ClickFix-style prompts or credential…
