POST /v1/prompt/guard

Prompt Guard

Flag instruction override attempts before they hit a tool.

Typed decisions, live

Pick a scenario, edit the input, run the real API. Choice, score, and yes/no come back with confidence.

Anonymous free runs: 1. Then sign in with Google or paste a laya_ key.

POST /v1/prompt/guard Live

State — the input software gives Laya

96c

Questions — typed decisions you get back

choice verdict

How should the guard treat this prompt?

noul override

Does it try to override prior instructions?

noul exfil

Does it try to extract hidden instructions or secrets?

Sample answers

sample · not yet run

allow72%

review14%

block14%

yes81%

no19%

yes81%

no19%