{"name":"SentryLLM · Watch the handoff from prompt to action","short_name":"SentryLLM","description":"SentryLLM traces the small moments that make an agent unsafe: a hidden instruction in retrieval, a tool call with too much reach, or a polished answer built on private context.","start_url":"/","scope":"/","display":"standalone","background_color":"#ffffff","theme_color":"#111113","categories":["security","developer","productivity"],"icons":[{"src":"/icon.svg","sizes":"any","type":"image/svg+xml","purpose":"any"}]}