jev-guard

Risk-scores every AI coding agent tool call in real time

Pluginfreemiumglobal

jev-guard is an auto-mode safety layer for coding agents, built on TypeSafe's Jev model, that risk-scores every tool call in real time (deny, ask, or allow), flags prompt injection hidden in results, and checks installed skills and plugins across tools like Claude Code, Codex, and Cursor. It's built for developers running agents in auto mode who want an automatic risk assessment instead of blind trust.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of jev-guard - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim jev-guard to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether jev-guard (or something else) actually fits.

Try a problem