PulseAugur
中
实时 03:44:49
English(EN) Does a Claude Code UserPromptSubmit hook keep a blocked prompt out of the transcript? 6 of 6 never reached the model, all 6 were still written to it

Claude Code 钩子未能从记录中删除被阻止的提示

一位用户发现,Claude Code 的 UserPromptSubmit 钩子(旨在阻止提示发送给模型)仍然会将这些被阻止的提示记录到会话记录中。尽管该钩子成功阻止了提示被模型处理,但在测试的六个提示中,全部六个都被写入了记录,其中一些甚至出现了两次。这种行为与文档中说明的功能相悖,文档指出被阻止的提示应从上下文中删除,并且不应添加到记录中。 AI

影响 此错误可能会影响用户信任和数据隐私,因为敏感信息可能会在被阻止后被无意中记录下来。

排序理由 该项目详细说明了软件产品功能的特定错误或意外行为,而不是新的发布或主要的行业发展。

在 dev.to — Claude Code tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Claude Code 钩子未能从记录中删除被阻止的提示

本文如何被排名

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目详细说明了软件产品功能的特定错误或意外行为,而不是新的发布或主要的行业发展。
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Rulestack ·

    Claude 代码用户提示提交钩子是否会将被阻止的提示排除在记录之外?6 个中的 6 个从未到达模型,但所有 6 个都被写入了它

    <blockquote> <p>6 of 6 prompts that a UserPromptSubmit hook blocked never reached the model, yet all 6 were still written to the session transcript (4 of them twice), and <code>claude -p</code> exited 0 with <code>"subtype": "success"</code> every time. Context injection matched …