io.github.loicfontaine-max/qorami
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands (15 of 150 labels to graduation). Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
Own this server? Screen its description →
QORAMI_API_KEYYour Qorami workspace API key (get one at https://qorami.fr/dashboard/).
Search companies, enrich contacts, and reveal emails and phones from your AI agent.
Send emails, track events, and manage contacts with MailJunky.
34-tool CRM server — contacts, pipeline, quotes, invoices, scheduling, email, and AI scoring.