安全与隐私

Anthropic and Accenture extend evaluation beyond model outputs to training, deployment, monitoring, and incident processes, with independence unresolved.

Anthropic 与 Accenture 的 embedded evaluator 计划把评测范围从模型输出扩展到训练、部署、监控和事故流程，也暴露出独立性边界。

Where keys belong when coding agents call GitHub, databases, and cloud APIs, and how vaults and credential brokers define access boundaries.

解释 Coding Agent 调用 GitHub、数据库和云 API 时，应用密钥、执行器密钥和第三方凭据该放在哪里，以及 Vault 与 Credential Broker 的边界。

AI agent engineering readings for September 11 to 18, 2026, with key findings, engineering implications, suggested sections, and primary sources.

覆盖 2026-09-11 至 09-18 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。

AI agent engineering readings for September 11 to 17, 2026, with key findings, engineering implications, suggested sections, and primary sources.

覆盖 2026-09-11 至 09-17 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。

覆盖 2026-09-11 至 09-16 的 AI Agent 工程阅读日志，保留本期重点、工程意义、优先阅读位置与一手来源。

AI agent engineering readings for September 11 to 16, 2026, with key findings, engineering implications, suggested sections, and primary sources.

How the Google Cloud Developer Plugin packages Skills, MCP configuration, and rules, and what this means for distribution, versions, and permissions.

拆解 Google Cloud Developer Plugin 如何把 Skill、MCP 配置和规则按 Agent Plugins 规范打包，暴露跨 Coding Agent 的分发、版本与权限问题。