AML.T0091.001 · Web Session Cookie

閱讀 MITRE ATLAS 中 AML.T0091.001「Web Session Cookie」相關的 1 個 AI 資安案例,查看事件證據、適用範圍與 AIDEFEND 防禦分析。

風險分類說明

Adversaries may use stolen web session cookies to authenticate to AI-enabled applications and supporting services as another user. This technique may bypass some multi-factor authentication controls because the session represented by the cookie has already been authenticated. Authentication cookies are commonly used by web applications and cloud-based services after a user has authenticated, allowing the user to continue using the service without repeatedly passing credentials. These cookies may remain valid for extended periods of time. After obtaining a cookie through [Steal Web Session Cookie](/techniques/AML.T0103), an adversary may import the cookie into a browser or automated client they control and access the corresponding application as the victim while the session remains active. In attacks on AI systems, web session cookies may grant access to AI chat histories, AI agent control panels, model provider dashboards, customer support systems, retrieval or knowledge management interfaces, or AI DevOps resources. If the stolen cookie belongs to an operator, support agent, developer, or administrator, the adversary may be able to view sensitive conversations, manipulate agent configuration, access private data available through AI tools, or perform actions with the victim account's permissions.

框架官方來源 ↗ · 開啟互動探索 ↗

Validated Research ·

以提示詞操弄在聯想 AI 聊天機器人上造成跨網站腳本攻擊

Cybernews 的研究人員示範了聯想的 AI 聊天機器人「Lena」有提示詞注入漏洞:它會產生惡意 HTML 並存進對話記錄中,之後在真人客服的瀏覽器中顯示時,就能把該客服的工作階段 cookie 外洩出去。 研究人員送給 Lena 的,是一個看起來人畜無害的產品資訊查詢,但其中夾帶了要求以危險 HTML 內容回覆的指示。這段回覆被存進使用者的對話記錄中,形成一個儲存型跨網站腳本(XSS)攻擊內容。當研究人員要求轉接真人客服時,客服照著正常流程打開對話記錄,就讓這段被投毒的內容顯示出來,把工作階段 cookie 的資料送到攻擊者控制的伺服器。如果一個仍然有效的客服 cookie 被重複使用,攻擊者就可能以該客服的身分登入聯想的客戶支援平台,查看客戶對話,或執行該帳號可用的其他操作。 聯想已承認這個問題,並表示已採取修正措施,以降低潛在影響並處理這個問題。

沿用 SecureFlow 來源步驟的 ATLAS 標註;不是 MITRE 對跨框架對應的背書。

SecureFlow · 閱讀完整案例 ↗