AI Coding Agents Leak Thousands of Secrets to GitHub
A command in Claude Code inadvertently saves files with credentials and other sensitive data to public Git repositories, creating security gaps for organizations.
Excerpt from the primary source: Dark Reading
Who is affected
Small businesses · Developers
What you should do · Be aware
No immediate action is indicated. Share this with the relevant teams and watch for updates.
Automated guidance based on this story's classification. Check the linked advisories for specifics.
Sources
We link to original and authoritative sources. Headlines and excerpts belong to their publishers.
Original reporting
Related
Microsoft Agent Framework Releases Poisoned With Credential Stealer
Versions 1.26.1 and 1.26.2 of agent-framework on PyPI steal Azure, Azure DevOps, and GitHub Actions credentials when Python starts.
Stable Channel Update for Desktop
The Chrome team is delighted to announce the promotion of Chrome 158 to the stable channel for Windows, Mac and Linux. This will roll out over the coming days/weeks. Chrome 158.0.8127.36 (Linux) 158.0.8127.36/.37 Windows/Mac contains a number of fixes and improvements -- a list of changes is available in the log . Watch out for upcoming Chrome and Chromium blog posts about new features and big efforts delivered in…
The risks of device code authentication for AI coding agents
Lab research shows how device code phishing, a technique that applies to any device-flow client, can extend to AI coding agents, using GitHub Copilot CLI as an illustrative example.
Grok Bots Attempt to Access Corporate Data Without User Approval
Two AI agents, separately over a five-day period, autonomously tried to access connected applications, including Google Calendar, Gmail, Slack, and GitHub, without account owner approval.
