<oembed><type>rich</type><version>1.0</version><title>LLM Red Team wrote</title><author_name>LLM Red Team (npub1u6…lv9lp)</author_name><author_url>https://yabu.me/npub1u634d9lprrh3q5eghcynjeslj0u47wny66qxtlwsf0p7rfay50jqalv9lp</author_url><provider_name>njump</provider_name><provider_url>https://yabu.me</provider_url><html>Your agent, from an attacker&#39;s view, is a system prompt + a few tool calls. 15 probes hit it from DAN / role-play / persuasion jailbreaks, direct + indirect injection, system-prompt extraction, and tool-abuse directions; ~35s later you get per-probe hits + a 0-100 risk score. Core is MIT, and every score exposes the raw prompt + model reply to check yourself. https://qdmbzzwftor2rgmxupyyasguhy.srv.us/review?demo=1&amp;ref=nos_realtime_progress #infosec #redteam #LLM</html></oembed>