Experimental News Clipping Site

Tag: vulnerabilities

  • Simon Willison’s Weblog: Why AI systems might never be secure

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/23/why-ai-systems-might-never-be-secure/#atom-everything Source: Simon Willison’s Weblog Title: Why AI systems might never be secure Feedly Summary: Why AI systems might never be secure The Economist have a new piece out about LLM security, with this headline and subtitle: Why AI systems might never be secure A “lethal trifecta” of conditions opens them to abuse…

  • The Register: ‘Technical debt’ in police database built to respond to child murders causing a ‘failing service’

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/22/police_database_built_to_respond/ Source: The Register Title: ‘Technical debt’ in police database built to respond to child murders causing a ‘failing service’ Feedly Summary: Project rated at ‘Red’ risk as it struggles to move off obsolete Oracle tech and cloud transition stalls The risk rating of the UK’s crime intelligence database is being elevated to…

  • The Register: FOMO? Brit banking biz rolls out AI tools, talks up security

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/22/lloyds_data_ai_deployment/ Source: The Register Title: FOMO? Brit banking biz rolls out AI tools, talks up security Feedly Summary: Lloyds Data and AI lead doesn’t want devs downloading models from the likes of Hugging Face – too risky Lloyds Banking Group is leaning into 21st century tech – yet trying to do so in…

  • Slashdot: AI Tools Give Dangerous Powers to Cyberattackers, Security Researchers Warn

    —

    by

    Kurt Seifried
    in

    Source URL: https://yro.slashdot.org/story/25/09/21/2022257/ai-tools-give-dangerous-powers-to-cyberattackers-security-researchers-warn?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: AI Tools Give Dangerous Powers to Cyberattackers, Security Researchers Warn Feedly Summary: AI Summary and Description: Yes **Summary:** The text highlights significant vulnerabilities associated with AI technologies, particularly in the context of automated systems and malicious actors leveraging them to exploit security gaps. It underscores emerging threats posed by…

  • Slashdot: Secure Software Supply Chains, Urges Former Go Lead Russ Cox

    —

    by

    Kurt Seifried
    in

    Source URL: https://developers.slashdot.org/story/25/09/21/0650219/secure-software-supply-chains-urges-former-go-lead-russ-cox?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Secure Software Supply Chains, Urges Former Go Lead Russ Cox Feedly Summary: AI Summary and Description: Yes Summary: The text emphasizes the critical need for enhancing software supply chain security, particularly in the face of ongoing vulnerabilities. It outlines practical solutions, such as adopting software signatures and reproducible builds,…

  • Slashdot: Cyberattack Delays Flights at Several of Europe’s Major Airports

    —

    by

    Kurt Seifried
    in

    Source URL: https://tech.slashdot.org/story/25/09/20/2119232/cyberattack-delays-flights-at-several-of-europes-major-airports?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Cyberattack Delays Flights at Several of Europe’s Major Airports Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a cyberattack that disrupted check-in and boarding systems across several major European airports, exposing vulnerabilities in these security systems. Despite limited impact on travelers, the incident highlights the ongoing…

  • Slashdot: Self-Replicating Worm Affected Several Hundred NPM Packages, Including CrowdStrike’s

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/09/20/0542237/self-replicating-worm-affected-several-hundred-npm-packages-including-crowdstrikes Source: Slashdot Title: Self-Replicating Worm Affected Several Hundred NPM Packages, Including CrowdStrike’s Feedly Summary: AI Summary and Description: Yes Summary: The Shai-Hulud malware campaign has affected numerous npm packages, including those maintained by CrowdStrike, via the injection of malicious scripts designed to steal developer credentials and exfiltrate sensitive information. The campaign highlights…

  • Simon Willison’s Weblog: Magistral 1.2

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/19/magistral/ Source: Simon Willison’s Weblog Title: Magistral 1.2 Feedly Summary: Mistral quietly released two new models yesterday: Magistral Small 1.2 (Apache 2.0, 96.1 GB on Hugging Face) and Magistral Medium 1.2 (not open weights same as Mistral’s other “medium" models.) Despite being described as "minor updates" to the Magistral 1.1 models these have…

  • Simon Willison’s Weblog: The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/19/notion-lethal-trifecta/ Source: Simon Willison’s Weblog Title: The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration Feedly Summary: The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration Abi Raghuram reports that Notion 3.0, released yesterday, introduces new prompt injection data exfiltration vulnerabilities…

  • The Register: ChatGPT joins human league, now solves CAPTCHAs for the right prompt

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/09/19/how_to_trick_chatgpt_agents/ Source: The Register Title: ChatGPT joins human league, now solves CAPTCHAs for the right prompt Feedly Summary: Could this bot-prevention technique now be obsolete? ChatGPT can be tricked via cleverly worded prompts to violate its own policies and solve CAPTCHA puzzles, potentially making this human-proving security mechanism obsolete, researchers say.… AI Summary…