Experimental News Clipping Site

Tag: injection

  • Simon Willison’s Weblog: New audio models from OpenAI, but how much can we rely on them?

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Mar/20/new-openai-audio-models/#atom-everything Source: Simon Willison’s Weblog Title: New audio models from OpenAI, but how much can we rely on them? Feedly Summary: OpenAI announced several new audio-related API features today, for both text-to-speech and speech-to-text. They’re very promising new models, but they appear to suffer from the ever-present risk of accidental (or malicious) instruction…

  • Alerts: CISA Adds Three Known Exploited Vulnerabilities to Catalog

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.cisa.gov/news-events/alerts/2025/03/19/cisa-adds-three-known-exploited-vulnerabilities-catalog Source: Alerts Title: CISA Adds Three Known Exploited Vulnerabilities to Catalog Feedly Summary: CISA has added three new vulnerabilities to its Known Exploited Vulnerabilities Catalog, based on evidence of active exploitation. CVE-2025-1316 Edimax IC-7100 IP Camera OS Command Injection Vulnerability CVE-2024-48248 NAKIVO Backup and Replication Absolute Path Traversal Vulnerability CVE-2017-12637 SAP NetWeaver Directory Traversal Vulnerability These…

  • The Cloudflare Blog: Cloudflare for AI: supporting AI adoption at scale with a security-first approach

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.cloudflare.com/cloudflare-for-ai-supporting-ai-adoption-at-scale-with-a-security-first-approach/ Source: The Cloudflare Blog Title: Cloudflare for AI: supporting AI adoption at scale with a security-first approach Feedly Summary: With Cloudflare for AI, developers, security teams and content creators can leverage Cloudflare’s network and portfolio of tools to secure, observe and make AI applications resilient and safe to use. AI Summary and…

  • The Register: Google acquisition target Wiz links fresh supply chain attack to 23K pwned GitHub repos

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/03/18/wiz_github_supply_chain/ Source: The Register Title: Google acquisition target Wiz links fresh supply chain attack to 23K pwned GitHub repos Feedly Summary: Ad giant’s cloudy arm to pay $30B in security shop deal Wiz security researchers think they’ve found the root cause of the GitHub supply chain attack that unfolded over the weekend, and…

  • Hacker News: Strengthening AI Agent Hijacking Evaluations

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.nist.gov/news-events/news/2025/01/technical-blog-strengthening-ai-agent-hijacking-evaluations Source: Hacker News Title: Strengthening AI Agent Hijacking Evaluations Feedly Summary: Comments AI Summary and Description: Yes Summary: The text outlines security risks related to AI agents, particularly focusing on “agent hijacking,” where malicious instructions can be injected into data handled by AI systems, leading to harmful actions. The U.S. AI Safety…

  • Schneier on Security: TP-Link Router Botnet

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/03/tp-link-router-botnet.html Source: Schneier on Security Title: TP-Link Router Botnet Feedly Summary: There is a new botnet that is infecting TP-Link routers: The botnet can lead to command injection which then makes remote code execution (RCE) possible so that the malware can spread itself across the internet automatically. This high severity security flaw (tracked…

  • Embrace The Red: Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates)

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/sneaky-bits-and-ascii-smuggler/ Source: Embrace The Red Title: Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates) Feedly Summary: You are likely aware of ASCII Smuggling via Unicode Tags. It is unique and fascinating because many LLMs inherently interpret these as instructions when delivered as hidden prompt injection, and LLMs can also emit them. Then,…

  • The Register: Expired Juniper routers find new life – as Chinese spy hubs

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/03/12/china_spy_juniper_routers/ Source: The Register Title: Expired Juniper routers find new life – as Chinese spy hubs Feedly Summary: Fewer than 10 known victims, but Mandiant suspects others compromised, too Chinese spies have for months exploited old Juniper Networks routers, infecting the buggy gear with custom backdoors and gaining root access to the compromised…