Experimental News Clipping Site

Tag: injection

  • The Register: Google declares AI bug hunting season open, sets a $30K max reward

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/10/07/google_ai_bug_bounty/ Source: The Register Title: Google declares AI bug hunting season open, sets a $30K max reward Feedly Summary: Jailbreaks, direct prompt injection not allowed Google on Monday rolled out a new AI Vulnerability Reward Program to encourage researchers to find and report flaws in its AI systems, with rewards of up to…

  • Cisco Talos Blog: Too salty to handle: Exposing cases of CSS abuse for hidden text salting

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.talosintelligence.com/too-salty-to-handle-exposing-cases-of-css-abuse-for-hidden-text-salting/ Source: Cisco Talos Blog Title: Too salty to handle: Exposing cases of CSS abuse for hidden text salting Feedly Summary: A simple yet effective tactic, known as hidden text salting, is increasingly used by cybercriminals over the past few months to evade even the most advanced email security solutions, including those powered…

  • Microsoft Security Blog: Investigating active exploitation of CVE-2025-10035 GoAnywhere Managed File Transfer vulnerability

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/10/06/investigating-active-exploitation-of-cve-2025-10035-goanywhere-managed-file-transfer-vulnerability/ Source: Microsoft Security Blog Title: Investigating active exploitation of CVE-2025-10035 GoAnywhere Managed File Transfer vulnerability Feedly Summary: Storm-1175, a financially motivated actor known for deploying Medusa ransomware and exploiting public-facing applications for initial access, was observed exploiting the deserialization vulnerability in GoAnywhere MFT’s License Servlet, tracked as CVE-2025-10035. We are publishing this…

  • Simon Willison’s Weblog: Sora 2 prompt injection

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Oct/3/cameo-prompt-injections/ Source: Simon Willison’s Weblog Title: Sora 2 prompt injection Feedly Summary: It turns out Sora 2 is vulnerable to prompt injection! When you onboard to Sora you get the option to create your own “cameo" – a virtual video recreation of yourself. Here’s mine singing opera at the Royal Albert Hall. You…

  • Microsoft Security Blog: Empowering defenders in the era of agentic AI with Microsoft Sentinel

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/09/30/empowering-defenders-in-the-era-of-agentic-ai-with-microsoft-sentinel/ Source: Microsoft Security Blog Title: Empowering defenders in the era of agentic AI with Microsoft Sentinel Feedly Summary: Microsoft Sentinel is expanding into an agentic platform with general availability of the Sentinel data lake, and the public preview of Sentinel graph and Sentinel Model Context Protocol (MCP) server.  The post Empowering defenders in the era of…

  • Schneier on Security: Abusing Notion’s AI Agent for Data Theft

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/09/abusing-notions-ai-agent-for-data-theft.html Source: Schneier on Security Title: Abusing Notion’s AI Agent for Data Theft Feedly Summary: Notion just released version 3.0, complete with AI agents. Because the system contains Simon Willson’s lethal trifecta, it’s vulnerable to data theft though prompt injection. First, the trifecta: The lethal trifecta of capabilities is: Access to your private…

  • Simon Willison’s Weblog: How to stop AI’s “lethal trifecta”

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/26/how-to-stop-ais-lethal-trifecta/ Source: Simon Willison’s Weblog Title: How to stop AI’s “lethal trifecta” Feedly Summary: How to stop AI’s “lethal trifecta” This is the second mention of the lethal trifecta in the Economist in just the last week! Their earlier coverage was Why AI systems may never be secure on September 22nd – I…

  • Docker: The Trust Paradox: When Your AI Gets Catfished

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.docker.com/blog/mcp-prompt-injection-trust-paradox/ Source: Docker Title: The Trust Paradox: When Your AI Gets Catfished Feedly Summary: The fundamental challenge with MCP-enabled attacks isn’t technical sophistication. It’s that hackers have figured out how to catfish your AI. These attacks work because they exploit the same trust relationships that make your development team actually functional. When your…