How did the Heapjack and Overpatch vulnerabilities discovered by Accomplish AI researchers let a malicious repository escape OpenAI Codex’sIllustration of the security boundary examined in the Heapjack and Overpatch research.
AI 提示
Create a landscape editorial hero image for this Studio Global article: How did the Heapjack and Overpatch vulnerabilities discovered by Accomplish AI researchers let a malicious repository escape OpenAI Codex’s. Article summary: Accomplish AI found two ways for content in an untrusted repository to cross Codex’s sandbox boundary. Heapjack could lead to unsandboxed command execution even in read-only mode; Overpatch could make Codex write outside. Topic tags: general, general web. Style: premium digital editorial illustration, source-backed research mood, clean composition, high detail, modern web publication hero. Use reference image context only for broad subject, composition, and topical grounding; do not copy the exact image. Avoid: logos, brand marks, copyrighted characters, real person likenesses, fake screenshots, UI text, readable text, watermarks, charts with fake numbers, click
openai.com
让 Codex 查看一个陌生代码仓库,并不等于只把仓库内容当作资料来读。Accomplish AI 发现,攻击者可控制的仓库内容能够借助 Codex 的高权限辅助工具,越过原本应限制其行为的沙箱。研究人员将两条不同的攻击路径命名为 Heapjack 和 Overpatch:前者甚至影响只读模式,后者则突破了工作区的写入范围。26