Experimental News Clipping Site

Tag: Unicode

  • Slashdot: How AI Coding Assistants Could Be Compromised Via Rules File

    —

    by

    Kurt Seifried
    in

    Source URL: https://developers.slashdot.org/story/25/03/23/2138230/how-ai-coding-assistants-could-be-compromised-via-rules-file?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: How AI Coding Assistants Could Be Compromised Via Rules File Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant security vulnerability in AI coding assistants like GitHub Copilot and Cursor, highlighting how malicious rule configuration files can be used to inject backdoors and vulnerabilities in…

  • Embrace The Red: Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates)

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/sneaky-bits-and-ascii-smuggler/ Source: Embrace The Red Title: Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates) Feedly Summary: You are likely aware of ASCII Smuggling via Unicode Tags. It is unique and fascinating because many LLMs inherently interpret these as instructions when delivered as hidden prompt injection, and LLMs can also emit them. Then,…

  • Hacker News: Grok 3 is highly vulnerable to indirect prompt injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/ Source: Hacker News Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Comments AI Summary and Description: Yes Summary: The text highlights significant vulnerabilities in xAI’s Grok 3 related to indirect prompt injection attacks, especially in the context of its operation on Twitter (X). This raises critical security concerns…

  • Simon Willison’s Weblog: Grok 3 is highly vulnerable to indirect prompt injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Feb/23/grok-3-indirect-prompt-injection/#atom-everything Source: Simon Willison’s Weblog Title: Grok 3 is highly vulnerable to indirect prompt injection Feedly Summary: Grok 3 is highly vulnerable to indirect prompt injection xAI’s new Grok 3 is so far exclusively deployed on Twitter (aka “X"), and apparently uses its ability to search for relevant tweets as part of every…

  • Hacker News: Smuggling arbitrary data through an emoji

    —

    by

    Kurt Seifried
    in

    Source URL: https://paulbutler.org/2025/smuggling-arbitrary-data-through-an-emoji/ Source: Hacker News Title: Smuggling arbitrary data through an emoji Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text discusses an interesting method of encoding data using Unicode characters, specifically through the application of variation selectors. This approach demonstrates a theoretical ability to embed arbitrary data within standard text representations,…

  • Embrace The Red: Security ProbLLMs in xAI’s Grok: A Deep Dive

    —

    by

    system automation
    in

    Source URL: https://embracethered.com/blog/posts/2024/security-probllms-in-xai-grok/ Source: Embrace The Red Title: Security ProbLLMs in xAI’s Grok: A Deep Dive Feedly Summary: Grok is the chatbot of xAI. It’s a state-of-the-art model, chatbot and recently also API. It has a Web UI and is integrated into the X (former Twitter) app, and recently it’s also accessible via an API.…

  • Cisco Talos Blog: Malicious QR codes

    —

    by

    system automation
    in

    Source URL: https://blog.talosintelligence.com/malicious_qr_codes/ Source: Cisco Talos Blog Title: Malicious QR codes Feedly Summary: QR codes are disproportionately effective at bypassing most anti-spam filters, as most filters are not designed to recognize that a QR code is present in an image and decode the QR code. According to Talos’ data, roughly 60% of all email containing…

  • Hacker News: Invisible text that AI chatbots understand and humans can’t?

    —

    by

    system automation
    in

    Source URL: https://arstechnica.com/security/2024/10/ai-chatbots-can-read-and-write-invisible-text-creating-an-ideal-covert-channel/ Source: Hacker News Title: Invisible text that AI chatbots understand and humans can’t? Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses a sophisticated method of exploiting vulnerabilities in AI chatbots like Claude and Copilot through “ASCII smuggling,” where invisible characters are used to embed malicious instructions. This innovative…