Urgent.News

What's breaking now, across thousands of outlets.

Saturday, 7 November 2026 Reading Room

AI

Claude Code's "Don't Ask Again" exposes passwords in 1,122 public GitHub files

Article URL: https://apiiro.com/blog/coding-agents-leaking-secrets-github-dont-ask-again Comments URL: https://news.ycombinator.com/item?id=50407882 Points: 238 # Comments: 152

apiiro.com ·

In osFoundry, viewers can see which Claude Code session requires their permission. When Claude Code reaches the prompt "Do you want to make this edit?", its card moves to the "Needs you" column after a second. Clicking on the card opens the panel for that prompt. Responding returns the card to the "Running" status.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at apiiro.com →

More in AI

在同一份 Note 裡，osFoundry 如何避免 Claude 的編輯蓋掉別人的編輯？

這是 Claude 對話在 osFoundry Notes 上可以用的寫入工具，內容取自公開 MCP endpoint 的列表。資料是 2026-11-06 用未驗證的 tools/list 抓下來的，只保留跟本文有關的欄位： { "name" : "edit_note_tab" , "description" : "Use an exact tab ID and version from…

  • osFoundry's Note tab prevents Claude's edits from overwriting others.
  • Required fields: noteid, tabid, expectedversion, idempotencykey.
  • Operation type determines action: replacetext, replacetabdata, etc.

·dev.to

I Spent 8 PRs Fixing My AI Fact-Checker. Then I Deleted All 12,852 Lines.

I asked AI to check AI. It cost more, caught nothing, and broke good articles. I run a few product sites where AI writes the articles. Power stations, gear, that kind of thing.

  • Author spent 8 PRs refining AI fact-checker, but it failed
  • Fact-checker blocked good articles with false alarms
  • Author deleted checker, removed 12,852 lines of code

·dev.to

Is Mandating AI Use in the Workplace Backfiring?

Some workplaces are holding mandatory AI training sessions, while others "are requiring employees to use a specific number of tokens," reports the Washington Post, "or log a certain amount of time on…

  • Mandating AI use may backfire, according to Stanford professor Arvind Karunakaran
  • Consuming many tokens doesn't guarantee substantial value creation
  • Employees may feel undervalued and disengaged without considering benefits

·it.slashdot.org

More from Saturday 7 November →