CVE-2026-12957 in Amazon Q is the third MCP auto-execution vulnerability in three AI coding tools. The pattern reveals a ...

GitHub’s actions/checkout v7 now blocks risky fork PR checkouts in privileged workflows to reduce common pwn request attacks.

Decades-old Bash shell tricks can bypass safeguards in most open source AI coding agents, creating a new software supply ...

Karpathy CLAUDE.md ten rules: a document attributed to Andrej Karpathy began circulating Friday, adding six agent self-check ...

The critical libssh2 CVE-2026-55200 flaw inverts SSH security: the remote server attacks the connecting client, no ...

A developer reverse-engineering Anthropic's Claude Code binary discovered on June 30, 2026, that the tool had been silently encoding hidden signals into its AI system prompts for at least three months ...

Chainguard is expanding Repository with new policy controls, malware and greyware scanning, and support for Java, Python, and container artifacts-helping organizations govern software consumption ...

Look to these tools to improve your AI coding practices and the quality, security, and reliability of your AI-generated code.

By targeting the automated workflows around repositories with targeted pull requests, attackers can potentially target ...

Cordyceps, a systemic class of exploitable CI/CD vulnerabilities, allows unauthenticated attackers to hijack developer ...

AI compressed the build. Fundamentals matter more, not less, and the product funnel is now where engineers earn their keep.