2. Linux.do
  3. 独立安全研究员，已利用Anthropic的Claude 入侵OpenAI

独立安全研究员，已利用Anthropic的Claude 入侵OpenAI

PSP 2026-09-18 12:46 1



破解OpenAI |Hacktron AI

最新回复 (6)
  • BlackCat 09-18 12:50
    1楼

    看来Anthropic的模型安全水平还有待提高 ^-^

  • Ys Ltr 09-18 12:51
    2楼

    这个漏洞仅仅价值 6500 美元？

  • 美丽心情2009 09-18 13:01
    3楼


    Warning

    Patch notice: If you self-host Discourse, rebuild your installation now. Older Docker images may contain a vulnerable libheif dependency that permits code execution through an image upload. Run git pull followed by ./launcher rebuild app from /var/discourse; a web-interface update alone may not replace the underlying image. Discourse-hosted customers have already been patched. See the security advisory.


  • Greem 09-18 13:09
    4楼

    看起来，克劳德模型确实有几把刷子

  • 啁啾 09-18 13:42
    5楼

    ^-^ 这么水灵灵地入侵么，openai 不出来叫唤几下


    都能拿到代码了顺便把4o拿出来呗

  • Serelene 09-18 13:44
    6楼

    openai在漏洞赏金计划非常 非常抠搜

* 帖子来源Linux.do
附近帖子
返回
飞读
随机推荐