AML.T0099 · AI Agent Tool Data Poisoning

閱讀 MITRE ATLAS 中 AML.T0099「AI Agent Tool Data Poisoning」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 manipulate data in a victim-controlled, trusted, or connected data source that is accessible through an AI agent tool. Poisoned data may be placed in document repositories, databases, source-code repositories, knowledge bases, search indexes, enterprise applications, or third-party data services used by the agent. The content may be crafted to appear in common tool queries or retrieval operations. It may contain false or misleading information or malicious instructions intended to produce an [LLM Prompt Injection: Indirect](/techniques/AML.T0051.001) when retrieved. This technique concerns manipulation of a data source that an agent tool treats as a source of information. When the adversary introduces the content through a victim-controlled public-facing application, the activity may also constitute [Prompt Infiltration via Public-Facing Application](/techniques/AML.T0093). Content retrieved directly from an adversary-controlled website may instead constitute [Drive-by Compromise](/techniques/AML.T0078). A malicious or compromised tool that deliberately alters its own runtime result constitutes [AI Agent Tool Poisoning: Runtime Response](/techniques/AML.T0110.002).

框架官方來源 ↗ · 開啟互動探索 ↗

Validated Research ·

偽造 Sentry 錯誤如何透過 MCP 誘導開發助理執行命令

Tenet Threat Labs 把這條攻擊稱為 Agentjacking:攻擊者可以用公開的 Sentry DSN 寫入偽造錯誤事件,再讓 Sentry MCP server 把這些事件帶進 AI coding agent 的工作流程;Sentry 是錯誤追蹤與可觀測性 (observability, 透過日誌、指標與執行追蹤,了解系統內部運作的能力)平台,這裡的事件原本只是診斷資料。當開發者要求 Claude Code、Cursor 或 Codex 調查 Sentry issue 時,agent 可能把事件裡偽裝成修復建議的文字當成可信診斷內容,進而執行攻擊者指定的 npm 命令。防禦重點不是把系統觀測資料(日誌、事件與監控資料)當成可信指令,而是在 MCP 輸出、agent 客戶端、工具權限、命令核准、沙箱和對外連線上一起設邊界。

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

AIA · 閱讀完整案例 ↗ · SecureFlow · 閱讀完整案例 ↗