Experimental News Clipping Site

Tag: control mechanism

  • Embrace The Red: Model Context Protocol – New Sneaky Exploit, Risks and Mitigations

    —

    by

    Kurt Seifried
    in

    Source URL: https://embracethered.com/blog/posts/2025/model-context-protocol-security-risks-and-exploits/ Source: Embrace The Red Title: Model Context Protocol – New Sneaky Exploit, Risks and Mitigations Feedly Summary: The Model Context Protocol (MCP) is a protocol definition for how LLM apps/agents can leverage external tools. I have been calling it Model Control Protocol at times, because due to prompt injection, MCP tool servers…

  • The Register: Bug hunter tricked SSL.com into issuing cert for Alibaba Cloud domain in 5 steps

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/04/22/ssl_com_validation_flaw/ Source: The Register Title: Bug hunter tricked SSL.com into issuing cert for Alibaba Cloud domain in 5 steps Feedly Summary: 10 other certificates ‘were mis-issued and have now been revoked’ Certificate issuer SSL.com’s domain validation system had an unfortunate bug that was exploited by miscreants to obtain, without authorization, digital certs for…

  • The Register: AI can’t stop making up software dependencies and sabotaging everything

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/04/12/ai_code_suggestions_sabotage_supply_chain/ Source: The Register Title: AI can’t stop making up software dependencies and sabotaging everything Feedly Summary: Hallucinated package names fuel ‘slopsquatting’ The rise of AI-powered code generation tools is reshaping how developers write software – and introducing new risks to the software supply chain in the process.… AI Summary and Description: Yes…

  • Hacker News: Gatehouse – a composable, async-friendly authorization policy framework in Rust

    —

    by

    Kurt Seifried
    in

    Source URL: https://github.com/thepartly/gatehouse Source: Hacker News Title: Gatehouse – a composable, async-friendly authorization policy framework in Rust Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses a flexible authorization library that integrates role-based (RBAC), attribute-based (ABAC), and relationship-based (ReBAC) access control policies. It emphasizes a multi-paradigm approach to access control, providing significant…

  • Hacker News: Why Tool AIs Want to Be Agent AIs (2016)

    —

    by

    Kurt Seifried
    in

    Source URL: https://gwern.net/tool-ai Source: Hacker News Title: Why Tool AIs Want to Be Agent AIs (2016) Feedly Summary: Comments AI Summary and Description: Yes Summary: The text presents a deep examination of the differing paradigms of autonomous AI systems, namely Agent AIs and Tool AIs, discussing their functionalities, risks, and economic implications. It highlights the…

  • Hacker News: Show HN: Codemcp – Claude Code for Claude Pro subscribers – ditch API bills

    —

    by

    Kurt Seifried
    in

    Source URL: https://github.com/ezyang/codemcp Source: Hacker News Title: Show HN: Codemcp – Claude Code for Claude Pro subscribers – ditch API bills Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text introduces “codemcp,” a tool designed to enhance the capability of the AI model Claude by acting as a pair programming assistant. It provides a…

  • NCSC Feed: Managing the risk of cloud-enabled products

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.ncsc.gov.uk/guidance/managing-risk-cloud-enabled-products Source: NCSC Feed Title: Managing the risk of cloud-enabled products Feedly Summary: Guidance outlining the risks of locally installed products interacting with cloud services, and suggestions to help organisations manage this risk. AI Summary and Description: Yes Summary: The text emphasizes the critical importance of understanding how deployed products interact with cloud…