Only firewall for AI prompts with a security grade on every PR

Name: Only firewall for AI prompts with a security grade on every PR
Availability: InStock
Author: acebot712

by acebot712·Mar 3, 2026·2 points·1 comment

Visit Project View on HN

AI Analysis

●●SolidSlickBig Brain

One-line SDK swap + PR red-teaming with A-F grades—but 'detect-and-block' gateway category is well-funded.

Strengths

•Red-team CI integration (autonomous attack mutation to find bypasses) is rare in commercial gateways
•Policy-as-Code flexibility avoids vendor lock-in—rules are auditable and version-controlled
•Real-time dashboard + cache optimization (showing actual $ savings) is DX above raw threat counts

Weaknesses

•20+ threat vectors is marketing—detections are well-known patterns (prompt injection, PII regexes, jailbreak keywords)
•Proxy latency (0.15s claimed) will add up across high-volume inference pipelines—cost-benefit unclear at scale
•Existing players (Robust Intelligence, Patronus, Lakera) have larger threat libraries and enterprise sales

Post Description

Every other gateway is detect-and-block. You don't get a security grade. You don't get red team in CI. We built the one that does.

PromptGuard is a proxy: change your base URL (one line with our SDK, or a few lines without), and every request gets checked for prompt injection, PII leaks, jailbreaks, and abuse. 20+ threat vectors, 39+ PII types. We also ship a red team suite and an autonomous agent that mutates attacks to find bypasses - you get a grade (A-F) and a GitHub Action that runs these tests on every PR. So you see where you're weak before you ship.

Works with OpenAI, Anthropic, Google, Azure, Gemini and more. Policy-as-Code. 10K free requests/month - link in the post.

Happy to answer questions.