Client-side hook model is bypassable and exposes data at the endpoint

[f5-aryan]

Context

All Codex hooks execute client-side ("in the GUI").

Problems

• Data is already at the client when hooks run — even a successful block is too late, and the payload could be captured by a malicious or competing hook written by a bad actor.
• Stop's enforcement is merely "you can no longer send prompts in this chat" — trivially bypassed by clicking new chat.

Analogy

This is client-side JS validation vs. a server-side WAF. Client-side means anyone can alter the logic — and the sensitive data has already reached the browser either way.

Impact

Client-side hooks are defense-in-depth at best, not a sound prevention/deterrence model for PII or harmful content.

Raised by a collaborator during Codex hook integration review.