Experimental News Clipping Site

Tag: proactive measures

  • Embrace The Red: Jules Zombie Agent: From Prompt Injection to Remote Control

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/google-jules-remote-code-execution-zombai/ Source: Embrace The Red Title: Jules Zombie Agent: From Prompt Injection to Remote Control Feedly Summary: In the previous post, we explored two data exfiltration vectors that Jules is vulnerable to and that can be exploited via prompt injection. This post takes it further by demonstrating how Jules can be convinced to…

  • The Register: Fortinet discloses critical bug with working exploit code amid surge in brute-force attempts

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/13/fortinet_discloses_critical_bug/ Source: The Register Title: Fortinet discloses critical bug with working exploit code amid surge in brute-force attempts Feedly Summary: If there’s smoke? Fortinet warned customers about a critical FortiSIEM bug that could allow an unauthenticated attacker to execute unauthorized commands, and said working exploit code for the flaw has been found in…

  • Slashdot: Sloppy AI Defenses Take Cybersecurity Back To the 1990s, Researchers Say

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/08/12/2037200/sloppy-ai-defenses-take-cybersecurity-back-to-the-1990s-researchers-say Source: Slashdot Title: Sloppy AI Defenses Take Cybersecurity Back To the 1990s, Researchers Say Feedly Summary: AI Summary and Description: Yes Summary: The text discusses the significant security risks associated with artificial intelligence, particularly at the Black Hat USA 2025 conference. As AI technologies such as large language models become prevalent, they…

  • Cloud Blog: Boosting defenders with AI: What’s coming at Security Summit 2025

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/identity-security/boosting-defenders-with-ai-whats-coming-at-security-summit-2025/ Source: Cloud Blog Title: Boosting defenders with AI: What’s coming at Security Summit 2025 Feedly Summary: While AI can help empower defenders, it can also create new security challenges. Those two critical, interconnected themes are driving our announcements and presentations for this year’s Google Cloud Security Summit.Join us live for Security Summit…

  • Slashdot: WSJ Finds ‘Dozens’ of Delusional Claims from AI Chats as Companies Scramble for a Fix

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/08/10/2023212/wsj-finds-dozens-of-delusional-claims-from-ai-chats-as-companies-scramble-for-a-fix?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: WSJ Finds ‘Dozens’ of Delusional Claims from AI Chats as Companies Scramble for a Fix Feedly Summary: AI Summary and Description: Yes Summary: The Wall Street Journal has reported on concerning instances where ChatGPT and other AI chatbots have reinforced delusional beliefs, leading users to trust in fantastical narratives,…

  • Embrace The Red: OpenHands and the Lethal Trifecta: Leaking Your Agent’s Secrets

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/openhands-the-lethal-trifecta-strikes-again/ Source: Embrace The Red Title: OpenHands and the Lethal Trifecta: Leaking Your Agent’s Secrets Feedly Summary: Another day, another AI data exfiltration exploit. Today we talk about OpenHands, formerly referred to as OpenDevin initially. It’s created by All-Hands AI. OpenHands renders images in chat, which enables zero-click data exfiltration during prompt injection…

  • OpenAI : Estimating worst case frontier risks of open weight LLMs

    —

    by

    Kurt Seifried
    in

    Source URL: https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms Source: OpenAI Title: Estimating worst case frontier risks of open weight LLMs Feedly Summary: In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and…