HackerNews中文版

我经常会对我的Claude Code可执行文件进行系统提示的补丁，以提高Claude的有效性。每次升级时，我都会请Claude自己分析新的二进制文件，寻找需要修改的问题系统提示。今天我在升级到v2.1.150时发现了一些相当令人担忧的事情： Claude Code现在允许Anthropic通过网络进行远程系统提示注入。有两个数据源。首先，在启动时调用api.anthropic.com/api/claude_cli/bootstrap的API，这个调用也会被缓存到磁盘。其次，是一个GrowthBook特性标志（tengu_heron_brook），每60秒刷新一次并进行后台同步。任何由这些端点返回的字符串都会被注入到具有shell访问权限的LLM模型的系统提示中。之前的版本也有注入点，但它们是死代码，仅返回null。我进行了二分查找，发现这个问题是在v2.1.150中引入的。更新日志上写着“内部基础设施改进（没有用户可见的变化）”，这真是轻描淡写。我已经尽我所能验证CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1可以阻止这一行为。我还将设置DISABLE_GROWTHBOOK=1以确保万无一失。验证命令： ``` npm pack @anthropic-ai/claude-code-linux-x64@2.1.150 --pack-destination /tmp tar xzf /tmp/anthropic-ai-claude-code-linux-x64-2.1.150.tgz strings package/claude | grep -oP 'function nAA\(\)\{[^}]+\}' strings package/claude | grep -oP '.{0,60}heron_brook.{0,60}' ``` nAA从磁盘读取缓存值。网络获取发生在启动时的函数n0A中。Rv("heron_brook", () => nAA())将其注册为系统提示的一部分，与所有核心行为指令一起。这些压缩的名称是特定于这个二进制文件的。

查看原文

I often patch the system prompts on my Claude Code executable in order to make Claude more effective. Every time I upgrade, I ask Claude himself to dissect the new binary and look for problematic system prompts to modify. Was upgrading to v2.1.150 today and discovered something that's rather alarming:Claude Code now allows Anthropic to perform remote system prompt injection via the network.Two data sources. First, API call to api.anthropic.com/api/claude_cli/bootstrap at startup, which also gets cached to disk. Second, a GrowthBook feature flag (tengu_heron_brook) that refreshes every 60 seconds with background sync. Any string returned by these endpoints gets injected into the system prompt of the LLM model with shell access.Previous versions also had an injection point, but they were dead code and simply returned null. Bisected it and found that this was introduced in v2.1.150. The changelog says "Internal infrastructure improvements (no user-facing changes)" which is quite the understatement.I've verified to the best of my ability that CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 blocks this. I will also be setting DISABLE_GROWTHBOOK=1 for good measure.Verification commands:<pre><code> npm pack @anthropic-ai/claude-code-linux-x64@2.1.150 --pack-destination /tmp tar xzf /tmp/anthropic-ai-claude-code-linux-x64-2.1.150.tgz strings package/claude | grep -oP 'function nAA\(\)\{[^}]+\}' strings package/claude | grep -oP '.{0,60}heron_brook.{0,60}' </code></pre> nAA reads the cached value from disk. The network fetch happens at startup in function n0A. Rv("heron_brook", () => nAA()) registers it as a section of the system prompt, alongside all the core behavioral instructions. These minified names are specific to this binary.

告诉HN：Claude Code 现在允许Anthropic远程注入系统提示。