Coding agents can clone a poisoned starter, read hostile content, leak private context into a public commit, or run a destructive GitHub command. Each action lo

> Open-source security framework for coding agents; addresses novel agentic risks

I open-sourced `agent-security` today.

Coding agents can clone a poisoned starter, read hostile content, leak private context into a public commit, or run a destructive GitHub command. Each action looks ordinary in isolation. The damage appears when trust crosses a boundary without a gate.

I wanted a small preflight layer I could inspect myself, run offline, and place before the expensive security tooling.

So I built five controls:

1. `scan` checks a repository before publication for credential shapes, private paths, invisible Unicode, and same-file decode-to-exec patterns.

2. `vet` inspe