Tool · curated 21 Jul 2026
GitHub - cgrtml/reasongate: Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.
First reported github.com
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
ReasonGate offers defenders a runnable guardrail that hardens LLM agents against prompt injection and unsafe tool calls with auditable decisions, useful for evaluating capability-based defenses.
ReasonGate is an open-source explainable security gate for LLM applications that aims to block prompt injection while emitting an auditable reason for every allow/deny decision. Beyond text detection, it adds a capability-based 'agent action gate' (framed around the lethal-trifecta) that blocks tool calls by argument taint even when detection misses reworded attacks, with a live playground and a documented threat model describing its guarantees and non-guarantees.