PulseAugur
中
实时 20:10:06
English(EN) While we're happy for our prize and that our exploit targeting OpenAI's Codex in the Coding Agent category was successful at # PWN2OWN , this was a collision💥 a

Doyensec 在 PWN2OWN 上利用 OpenAI Codex,但该漏洞早已知晓

Doyensec 在 PWN2OWN 竞赛的编码代理类别中成功利用了 OpenAI 的 Codex 模型。然而,此次漏洞利用是基于先前已披露的漏洞,导致该团队称之为一次“意外”。他们现在将返回进行进一步研究。 AI

影响 凸显了 AI 编码助手潜在的漏洞,强调了持续安全研究和修补的必要性。

排序理由 该集群描述了在安全竞赛中成功利用 AI 模型,这是一种研究里程碑。 [lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Doyensec 在 PWN2OWN 上利用 OpenAI Codex,但该漏洞早已知晓

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了在安全竞赛中成功利用 AI 模型,这是一种研究里程碑。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
147 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    尽管我们为在#PWN2OWN的Coding Agent类别中成功利用OpenAI的Codex感到高兴,但这却是一次碰撞💥

    While we're happy for our prize and that our exploit targeting OpenAI's Codex in the Coding Agent category was successful at # PWN2OWN , this was a collision💥 as the bug was previously known to the vendor. Back to the research! # P2OBerlin # doyensec # appsec # security # ai # op…