31,088 secrets in Claude Code's .claude/settings.local.json on public GitHub
What happened
GitGuardian discovered over 31,000 instances of sensitive API keys and secrets exposed publicly on GitHub inside Claude Code's local settings files. This oversight occurred because developers inadvertently committed configuration files containing credentials generated by Anthropic's new CLI tool.
Why it matters
This highlights the urgent need for better security guardrails and secret management in developer-focused AI tools. As AI coding assistants proliferate, accidental credential leaks will remain a major attack vector unless default configurations prioritize security.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Anthropic
Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-FreeAnthropic · 14 Nov 2026Claude designed FPGA scaler board for 6th-gen consolesAnthropic · 13 Nov 2026I asked Claude Fable 5.2 to turn my site into a 90s Silicon Graphics workstationAnthropic · 13 Nov 2026Anthropic is endorsing SB 53Anthropic · 13 Nov 2026Understanding and addressing AI harmsAnthropic · 13 Nov 2026This page was collected from blog.gitguardian.com and summarised automatically by AIPulsee's pipeline. See how it runs.