Experimental News Clipping Site

Tag: Exploitation

  • Cisco Security Blog: Detecting Exposed LLM Servers: A Shodan Case Study on Ollama

    —

    by

    Kurt Seifried
    in

    Source URL: https://feedpress.me/link/23535/17131153/detecting-exposed-llm-servers-shodan-case-study-on-ollama Source: Cisco Security Blog Title: Detecting Exposed LLM Servers: A Shodan Case Study on Ollama Feedly Summary: We uncovered 1,100+ exposed Ollama LLM servers—20% with open models—revealing critical security gaps and the need for better LLM threat monitoring. AI Summary and Description: Yes Summary: The text highlights the discovery of over 1,100…

  • Embrace The Red: Wrap Up: The Month of AI Bugs

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/wrapping-up-month-of-ai-bugs/ Source: Embrace The Red Title: Wrap Up: The Month of AI Bugs Feedly Summary: That’s it. The Month of AI Bugs is done. There won’t be a post tomorrow, because I will be at PAX West. Overview of Posts ChatGPT: Exfiltrating Your Chat History and Memories With Prompt Injection | Video ChatGPT…

  • Embrace The Red: AgentHopper: An AI Virus Research Project

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/agenthopper-a-poc-ai-virus/ Source: Embrace The Red Title: AgentHopper: An AI Virus Research Project Feedly Summary: As part of the Month of AI Bugs, serious vulnerabilities that allow remote code execution via indirect prompt injection were discovered. There was a period of a few weeks where multiple arbitrary code execution vulnerabilities existed in popular agents,…

  • The Register: Researcher who found McDonald’s free-food hack turns her attention to Chinese restaurant robots

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/29/pudu_robots_hackable/ Source: The Register Title: Researcher who found McDonald’s free-food hack turns her attention to Chinese restaurant robots Feedly Summary: The admin controls were left wide open on Pudu’s robots A researcher caught the world’s leading supplier of commercial service robots using shoddy admin security that let attackers redirect the delivery machines to…

  • Slashdot: Defense Department Reportedly Relies On Utility Written by Russian Dev

    —

    by

    Kurt Seifried
    in

    Source URL: https://tech.slashdot.org/story/25/08/27/2026245/defense-department-reportedly-relies-on-utility-written-by-russian-dev?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Defense Department Reportedly Relies On Utility Written by Russian Dev Feedly Summary: AI Summary and Description: Yes Summary: The article highlights concerns over the fast-glob utility, widely used in Node.js applications, particularly within U.S. Department of Defense systems. Maintained by a Russian developer with ties to Yandex, the lack…

  • Cisco Talos Blog: Libbiosig, Tenda, SAIL, PDF XChange, Foxit vulnerabilities

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.talosintelligence.com/libbiosig-tenda-sail-pdf-xchange-foxit-vulnerabilities/ Source: Cisco Talos Blog Title: Libbiosig, Tenda, SAIL, PDF XChange, Foxit vulnerabilities Feedly Summary: Cisco Talos’ Vulnerability Discovery & Research team recently disclosed ten vulnerabilities in BioSig Libbiosig, nine in Tenda AC6 Router, eight in SAIL, two in PDF-XChange Editor, and one in a Foxit PDF Reader.The vulnerabilities mentioned in this blog…

  • Slashdot: One Long Sentence is All It Takes To Make LLMs Misbehave

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/08/27/1756253/one-long-sentence-is-all-it-takes-to-make-llms-misbehave?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: One Long Sentence is All It Takes To Make LLMs Misbehave Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant security research finding from Palo Alto Networks’ Unit 42 regarding vulnerabilities in large language models (LLMs). The researchers explored methods that allow users to bypass…