Reef Prompt Guard

Detect and filter prompt injection attacks in untrusted input. Use when processing external content (emails, web scrapes, API inputs, Discord messages, sub-agent outputs) or when building systems that accept user-provided text that will be passed to an LLM. Covers direct injection, jailbreaks, data exfiltration, privilege escalation, and context manipulation.

Alert Triage

Normalize and classify alerts by urgency, trust, and audience to decide send-now, batch-later, ignore, suppress-as-duplicate, or escalate actions.