7 min read
Let an Open-Weight Model Audit Your Code, but Do Not Give It the Keys
How to run a nightly AI security audit without giving the model credentials, production access or authority to merge its own fixes.
Blog posts tagged
SECURITYPage 1
5 min read
Delay Routine Dependency Updates, Not Security Fixes
Use a short cooldown for routine dependency releases while keeping known security fixes on the fast path.
5 min read
The Pull Request Can Now Rewrite Its Own AI Reviewer
Why pull-request-controlled AI review instructions collapse a trust boundary, and how teams can restore it without giving up useful repository context.
4 min read
Government Review of AI Models Needs Clear Limits
US review of frontier model releases can reduce specific security risks, but delays need public criteria, time limits and proportionate controls.
3 min read
We Had This Argument in 1995: Restricting Cybersecurity AI Is a Losing Game
Gated cyber models may buy defenders time, but history suggests the advantage will not last.
6 min read
We Gave AI the Keys to Production. Now What?
AI coding tools and autonomous agents are shipping faster than the guardrails meant to govern them. Here is where the risks are and what thoughtful adoption looks like.
3 min read
Use a Public SSH Server as a SOCKS Proxy on macOS
Create a secure, temporary SOCKS proxy from your Mac with SSH dynamic port forwarding and simple start/stop commands.
4 min read
The Most Common Secret-Leaking Patterns I Still See in 2026
The repeat mistakes that still leak API keys, tokens, and credentials into Git and logs, plus practical fixes.