OpenClaw 透過提示詞注入建立命令與控制通道
研究人員證實,藏在網頁中的間接提示詞注入攻擊(indirect prompt injection),可以使 OpenClaw 執行惡意指令碼、污染後續 agent 上下文,並像命令與控制 agent 一樣運作。
沿用 SecureFlow 來源步驟的 ATLAS 標註;不是 MITRE 對跨框架對應的背書。
AI SECURITY CASES × FRAMEWORKS
閱讀 MITRE ATLAS 中 AML.T0002.002「AI Agent Configuration」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。
Adversaries may acquire publicly accessible AI agent configuration files to understand agent capabilities, gain unauthorized access to tools and data sources, or identify credentials for further attacks. Configuration files define what tools an agent can use, credentials for external services, system prompts, and behavioral settings, making them valuable resources for adversaries targeting AI agent deployments. Once configuration files are acquired, adversaries may perform [Discover AI Agent Configuration](/techniques/AML.T0084) to gain additional insights they can use in their operation or [Credentials from AI Agent Configuration](/techniques/AML.T0083) to harvest secrets. AI agent configuration files come in multiple forms depending on the platform and agent framework. Agent configuration files adversaries may target include: - System prompts: Files containing agent instructions, behavioral guidelines, and internal logic. - Tool configuration: Files defining tools the agent can utilize, including Model Context Protocol (MCP) configs (e.g., `mcp.json`, `claude_desktop_config.json`), IDE-specific configs (e.g., `.claude/settings.json`, `.vscode/tasks.json`), and framework-specific settings that define external tool and data source integrations. - Skills and workflows: Files defining agent capabilities, behaviors, or workflows. Often a combination of instructions, scripts, and resources. - Environment and deployment configs: Files that control agent deployment and runtime behavior, often environment variables or framework-specific configs.
研究人員證實,藏在網頁中的間接提示詞注入攻擊(indirect prompt injection),可以使 OpenClaw 執行惡意指令碼、污染後續 agent 上下文,並像命令與控制 agent 一樣運作。
沿用 SecureFlow 來源步驟的 ATLAS 標註;不是 MITRE 對跨框架對應的背書。