Subscribe
LIVE FEED
▸Anthropic Sets IPO Range of $70 to $78 Per Share, Implying $1.404 Trillion Value▸Google Releases Gemini 4 Carbon to the Public With an Agent 'Swarm' Feature▸DeepMind's AlphaProof Code Verifies Signal's Core Encryption With 3 Million Lines of Proofs▸OpenAI Launches Businesses in ChatGPT, Including Verified Business Agents▸Anthropic Launches Claude Meetings as Part of Its New AI Office Suite▸New York's AI Safety Law Takes Effect, Putting OpenAI and Anthropic Under Oversight▸Nvidia Opens Probe Into CEO Jensen Huang Over Ties to Suspected Chinese Spy▸Anthropic Launches Claude Fable 5.2 and Mythos 5.2 With Faster Outputs
Briefing presented by your brand
← All news
Research & Safety

Claude Code Prompt Is Accidentally Exposing Secrets on GitHub

Ars Technica reports that a "Do not ask again" prompt in Claude Code leads to passwords, API keys and other secrets being shared on GitHub.

10 Nov 20262 min readSource: Ars Technica
RESEARCH & SAFETY

Ars Technica reports that Claude Code is accidentally exposing secrets across GitHub. The cause is a "Do not ask again" prompt.

When users choose that option, passwords, API keys and other sensitive data end up being shared. The report says this is happening widely on the platform.

Why it matters: A single permission click could leak credentials from your repos, so check your settings.

What builders should know

  • Be careful with "Do not ask again" choices in AI coding tools.
  • Check your repos for exposed passwords and API keys.

Sources: Ars Technica