Experimental News Clipping Site

Tag: risks

  • 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…

  • Simon Willison’s Weblog: When a Jira Ticket Can Steal Your Secrets

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Aug/9/when-a-jira-ticket-can-steal-your-secrets/ Source: Simon Willison’s Weblog Title: When a Jira Ticket Can Steal Your Secrets Feedly Summary: When a Jira Ticket Can Steal Your Secrets Zenity Labs describe a classic lethal trifecta attack, this time against Cursor, MCP, Jira and Zendesk. They also have a short video demonstrating the issue. Zendesk support emails are…

  • Slashdot: AI Industry Horrified To Face Largest Copyright Class Action Ever Certified

    —

    by

    Kurt Seifried
    in

    Source URL: https://yro.slashdot.org/story/25/08/08/2040214/ai-industry-horrified-to-face-largest-copyright-class-action-ever-certified?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: AI Industry Horrified To Face Largest Copyright Class Action Ever Certified Feedly Summary: AI Summary and Description: Yes **Summary:** The text discusses the potential repercussions of a major copyright class action lawsuit against Anthropic, which could significantly impact the entire AI industry. Claims from industry groups suggest that if…

  • The Register: Meet President Willian H. Brusen from the great state of Onegon

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/08/gpt-5-fake-presidents-states/ Source: The Register Title: Meet President Willian H. Brusen from the great state of Onegon Feedly Summary: LLMs still struggle with accurate text within graphics hands on OpenAI’s GPT-5, unveiled on Thursday, is supposed to be the company’s flagship model, offering better reasoning and more accurate responses than previous-gen products. But when…

  • Wired: A Misconfiguration That Haunts Corporate Streaming Platforms Could Expose Sensitive Data

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/corporate-livestreams-exposed-search-tool/ Source: Wired Title: A Misconfiguration That Haunts Corporate Streaming Platforms Could Expose Sensitive Data Feedly Summary: A security researcher discovered that flawed API configurations are plaguing corporate livestreaming platforms, potentially exposing internal company meetings—and he’s releasing a tool to find them. AI Summary and Description: Yes Summary: The text highlights a security…

  • The Register: Infosec hounds spot prompt injection vuln in Google Gemini apps

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/08/infosec_hounds_spot_prompt_injection/ Source: The Register Title: Infosec hounds spot prompt injection vuln in Google Gemini apps Feedly Summary: Not a very smart home: crims could hijack smart-home boiler, open and close powered windows and more. Now fixed Black hat A trio of researchers has disclosed a major prompt injection vulnerability in Google’s Gemini large…

  • The Register: OpenAI’s GPT-5 is here with up to 80% fewer hallucinations

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/07/openai_gpt_5/ Source: The Register Title: OpenAI’s GPT-5 is here with up to 80% fewer hallucinations Feedly Summary: That totally makes up for the single-digit benchmark gains, right? OpenAI unveiled its most capable model yet on Thursday with the launch of GPT-5.… AI Summary and Description: Yes Summary: The announcement of OpenAI’s GPT-5 represents…

  • Slashdot: Encryption Made For Police and Military Radios May Be Easily Cracked

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/08/07/217234/encryption-made-for-police-and-military-radios-may-be-easily-cracked Source: Slashdot Title: Encryption Made For Police and Military Radios May Be Easily Cracked Feedly Summary: AI Summary and Description: Yes Summary: The text highlights critical vulnerabilities in an encryption algorithm widely used in radios for essential sectors, including law enforcement and military. After researchers discovered a backdoor in the original algorithm,…