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
叫 Codex「只睇唔改」,是否就可以放心檢查陌生人的程式庫?Accomplish AI 發現的兩個漏洞顯示,答案不能單靠唯讀設定決定:攻擊者可藉由受其控制的程式庫內容,觸及權限高於該程式庫的 Codex 輔助工具。Heapjack 可由唯讀模式走到開發者電腦,執行未受沙盒限制的指令;Overpatch 則可繞過專案目錄的寫入界線。兩條路徑不同,都不需要開發者批准相關操作。26