写作
安全与隐私
筛选文章 安全与隐私
安全与隐私
第 4 页 · 12 / 72-
Link CLI lets agents pay without real card numbers Stripe Link CLI separates purchase intent from payment permission. Agents request a purchase and receive one-time credentials only after user approval.
-
Link CLI 让 Agent 付款,但不拿真实卡号 Stripe Link CLI 让 Agent 先提交购买请求,用户确认后再获得本次支付需要的一次性凭证,把购买意图和支付权限分开。
-
AI Agent 工程阅读清单|2026-09-23 本期收录 GitHub Copilot 本地 Sandbox、Agensh、CliffCompaction、SWE-Serve,以及 Copilot OpenTelemetry。
-
AI agent engineering reading list | 2026-09-23 GitHub Copilot local sandboxing, Agensh, CliffCompaction, SWE-Serve, and enterprise OpenTelemetry support in the Copilot app.
-
Why pinning a Git SHA can still run different code Plugin4Shell exposes a supply-chain gap: a pinned SHA records the expected version, but installers must also verify the actual HEAD after checkout.
-
固定 Git SHA 为什么还可能跑到别的代码 Plugin4Shell 暴露了一个供应链边界:固定 SHA 只写下期望版本,安装器还必须在 checkout 后验证真实 HEAD。本文结合 Git 文档、本地无害复现和 GitHub 分支限制解释机制。
-
AI agent engineering reading list | 2026-09-21 LangGraph human-approval schemas, Deep Agents safeguards for parallel writes to the same file, and tighter OAuth boundaries in the MCP Ruby SDK.
-
AI Agent 工程阅读清单|2026-09-21 本期收录 LangGraph 人工审批结构约束、Deep Agents 同文件并行写保护,以及 MCP Ruby SDK OAuth 边界收紧。
-
AI agent engineering reading list | 2026-09-18 to 09-20 OpenAI Agents SDK runtime-boundary fixes, stage-aware memory retrieval in AdaRepair-Mem, and static configuration checks with Agent Lint.
-
AI Agent 工程阅读清单|2026-09-18 至 09-20 本期收录 OpenAI Agents SDK 运行时边界修复、AdaRepair-Mem 阶段化记忆检索,以及 Agent Lint 静态配置检查。
-
OpenCloak: replace personal data before sending it to AI OpenCloak replaces names, emails, and other personal data with stable stand-ins locally, then restores them when the model responds.
-
OpenCloak:发给 AI 之前,先在本地把个人信息换成假值 OpenCloak 在本地把姓名、邮箱等敏感字段替换成稳定假值,模型响应回来后再恢复,减少个人信息直接发送给 AI 服务。