23 articles tagged with AI Agents.
Coding agents call git status for context, and a hostile repository can make that run any program it names, outside the sandbox and without a prompt. Here is which agents are patched and how to protect yourself today.
A Harvard study of 718 firms found coding agents raise code output 30% while shipped work barely moves. The gains are stuck in code review. Here is how to unstick them.
GitHub made local sandboxing generally available for Copilot CLI on October 7, so the default now restricts the agent instead of trusting it.
It is OAuth for letting your AI agent act on your behalf with a business, not another MCP, and it is nowhere near ready to build on.
A compromised npm release went after cloud credentials as expected, and local AI coding-assistant config files, which most teams never treated as secrets.
Mods make Claude Code a real runtime you can program. They also run with your full native permissions, no sandbox, so a bad one is a bad CI step.
Google shipped a 1M-token output ceiling and strong cyber-defense benchmarks, then handed the keys to almost nobody. Here is what that gating pattern tells you.
Same sticker price, a real-world cost drop from speed and token efficiency. Here is who should move today and who can wait a sprint.
Docker put AI coding agents in hosted microVMs instead of containers, because a container was never the isolation boundary this job needed.
Zed says agents made pull requests obsolete and shipped Delta to replace them. The review unit needs rethinking, but review itself, and the gates around it, stay.
Handing an agent kubectl is a five-minute job. Proving the fix worked and did no harm is the real work, and it belongs in the wrapper, not the prompt.
A SHA pin that nobody checks is a label, not a control. Plugin4Shell showed that four major coding agents never checked.
