AINewsnow

Secrets leaking through coding-agent permission prompts, Apirio finds

This story is from 2026-11-05. It is preserved in the archive; the latest stories are on the live feed.

Apirio reported that passwords were committed in over a thousand public GitHub files, leaking through coding-agent permission prompts.

Read the full story at DEV Community — AI ↗

Timeline · 7 reports

  1. 2026-11-08 04:46 · DEV Community — AI
    Dev News Digest: 8 Nov 2026, 06:00
  2. 2026-11-07 10:47 · DEV Community — AI
    Dev News Digest: 7 Nov 2026, 12:00
  3. 2026-11-07 04:47 · DEV Community — AI
    Dev News Digest: 7 Nov 2026, 05:00
  4. 2026-11-06 10:48 · DEV Community — AI
    Dev News Digest: 6 Nov 2026, 12:00
  5. 2026-11-06 04:47 · DEV Community — AI
    Dev News Digest: 6 Nov 2026, 06:00
  6. 2026-11-05 16:47 · DEV Community — AI
    Dev News Digest: 5 Nov 2026, 18:00
  7. 2026-11-05 10:47 · DEV Community — AI
    Dev News Digest: 5 Nov 2026, 12:00

More stories

  1. Coding agents leak secrets through permission prompts, security research finds — DEV Community — AI
  2. Claude Code's 'Don't Ask Again' file exposed thousands of secrets in public GitHub repos — The Hacker News (security)
  3. Claude Code privacy bug exposed users' email addresses to third parties — DEV Community — AI
  4. Claude Code drives wave of community-built apps, tools and workflows — DEV Community — AI
  5. AI Coding Agents Shift From Prompt Files to Deterministic Scripts and Sandboxed Execution — DEV Community — AI
  6. Anthropic launches Claude Personal Finance in the US with read-only bank access — Engadget
  7. DeepSeek V4.1 Flash gains traction across local rigs, benchmarks, and serving platforms — Vercel Blog
  8. Perplexity launches Teammates, always-on AI agents for ongoing work — The Verge AI

Get the daily brief of stories like this at 6:30 every morning →