Show HN: ReasonGate- An explainable gate that blocks LLM prompt injection
ReasonGate is a new open-source security tool designed to detect and block prompt injection attacks in LLM applications. It provides explainable, rule-based reasoning for its security decisions, aiming to help developers meet audit and compliance requirements.
Why it matters
As LLMs are integrated into enterprise workflows, robust and auditable security layers are critical to preventing malicious manipulation of AI agents.
An explainable security gate for LLM applications. Every decision carries a reason you can audit.
A bank support agent has tools ( send_email , transfer_funds ) and is handed a customer record with a hidden instruction inside it (indirect injection the dominant attack on RAG / agents). Same attack, one variable: the shield.
The proof isn't the agent's words it's the side effects that did not happen . Run it yourself (deterministic, no API key needed); it's a CI-enforced invariant , not a screenshot:
python -m examples.stakes_demo.run # see examples/stakes_demo/ ▶ Try the live demo — paste a prompt, watch it get blocked with a reason and an auditable record See it block a direct attack or a hidden, zero-width-obfuscated one — runs on the zero-dependency core, no API keys, no data leaves the server.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in