Coding agents leak secrets through permission prompts, security research finds
Apiiro reported passwords committed in over a thousand public GitHub files, linked to secrets exposed via coding-agent permission prompts.
Read the full story at DEV Community — AI ↗
Timeline · 7 reports
- 2026-11-08 16:47 · DEV Community — AI
Dev News Digest: 8 Nov 2026, 18:00 - 2026-11-08 10:47 · DEV Community — AI
Dev News Digest: 8 Nov 2026, 11:00 - 2026-11-08 04:46 · DEV Community — AI
Dev News Digest: 8 Nov 2026, 06:00 - 2026-11-07 10:47 · DEV Community — AI
Dev News Digest: 7 Nov 2026, 12:00 - 2026-11-07 04:47 · DEV Community — AI
Dev News Digest: 7 Nov 2026, 05:00 - 2026-11-06 10:48 · DEV Community — AI
Dev News Digest: 6 Nov 2026, 12:00 - 2026-11-06 04:47 · DEV Community — AI
Dev News Digest: 6 Nov 2026, 06:00
More stories
- Claude Code's 'Don't Ask Again' file exposed thousands of secrets in public GitHub repos — The Hacker News (security)
- Claude Code privacy bug exposed users' email addresses to third parties — DEV Community — AI
- Claude Code drives wave of community-built apps, tools and workflows — DEV Community — AI
- AI Coding Agents Shift From Prompt Files to Deterministic Scripts and Sandboxed Execution — DEV Community — AI
- Anthropic launches Claude Personal Finance in the US with read-only bank access — Engadget
- DeepSeek V4.1 Flash gains traction across local rigs, benchmarks, and serving platforms — Vercel Blog
- Perplexity launches Teammates, always-on AI agents for ongoing work — The Verge AI
- Dedicated AI voice recorders gain ground over phone apps with local AI and zero-cloud privacy — DEV Community — AI
Get the daily brief of stories like this at 6:30 every morning →