Experimental News Clipping Site

Tag: prompt

  • Simon Willison’s Weblog: GPT-5 has a hidden system prompt

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Aug/15/gpt-5-has-a-hidden-system-prompt/#atom-everything Source: Simon Willison’s Weblog Title: GPT-5 has a hidden system prompt Feedly Summary: GPT-5 has a hidden system prompt It looks like GPT-5 when accessed via the OpenAI API may have its own hidden system prompt, independent from the system prompt you can specify in an API call. At the very least…

  • The Register: Typhoon-adjacent Chinese crew broke into Taiwanese web host

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/15/typhoonadjacent_chinese_crew_taiwan_web_servers/ Source: The Register Title: Typhoon-adjacent Chinese crew broke into Taiwanese web host Feedly Summary: Is that a JuicyPotato on your network? A suspected Chinese-government-backed cyber crew recently broke into a Taiwanese web hosting provider to steal credentials and plant backdoors for long-term access, using a mix of open-source and custom software tools,…

  • The Register: Cisco’s Secure Firewall Management Center now not-so secure, springs a CVSS 10 RCE hole

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/15/cisco_secure_firewall_management_bug/ Source: The Register Title: Cisco’s Secure Firewall Management Center now not-so secure, springs a CVSS 10 RCE hole Feedly Summary: Switchzilla’s summer of perfect 10s Cisco has issued a patch for a maximum-severity bug in its Secure Firewall Management Center (FMC) software that could allow an unauthenticated, remote attacker to inject arbitrary…

  • Embrace The Red: Google Jules is Vulnerable To Invisible Prompt Injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/google-jules-invisible-prompt-injection/ Source: Embrace The Red Title: Google Jules is Vulnerable To Invisible Prompt Injection Feedly Summary: The latest Gemini models quite reliably interpret hidden Unicode Tag characters as instructions. This vulnerability, first reported to Google over a year ago, has not been mitigated at the model or API level, hence now affects all…

  • The Register: LLM chatbots trivial to weaponise for data theft, say boffins

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/15/llm_chatbots_trivial_to_weaponise/ Source: The Register Title: LLM chatbots trivial to weaponise for data theft, say boffins Feedly Summary: System prompt engineering turns benign AI assistants into ‘investigator’ and ‘detective’ roles that bypass privacy guardrails A team of boffins is warning that AI chatbots built on large language models (LLM) can be tuned into malicious…

  • The Register: Dodgy Huawei chips nearly sunk DeepSeek’s next-gen R2 model

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/14/dodgy_huawei_deepseek/ Source: The Register Title: Dodgy Huawei chips nearly sunk DeepSeek’s next-gen R2 model Feedly Summary: Chinese AI model dev still plans to use homegrown silicon for inferencing Unhelpful Huawei AI chips are reportedly why Chinese model dev DeepSeek’s next-gen LLMs are taking so long.… AI Summary and Description: Yes Summary: The text…

  • Docker: MCP Horror Stories: The GitHub Prompt Injection Data Heist

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.docker.com/blog/mcp-horror-stories-github-prompt-injection/ Source: Docker Title: MCP Horror Stories: The GitHub Prompt Injection Data Heist Feedly Summary: This is Part 3 of our MCP Horror Stories series, where we examine real-world security incidents that validate the critical vulnerabilities threatening AI infrastructure and demonstrate how Docker MCP Toolkit provides enterprise-grade protection. The Model Context Protocol (MCP)…