reasongate
面向 LLM 应用的可解释安全网关 — 拦截提示注入，并为每个决策提供可审计的理由。
Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.
怎么安装
暂无统一安装命令，请查看仓库 README。
简介
ReasonGate A self-hostable gate that inspects the text going into and out of an LLM and returns an explainable allow / flag / block decision with a machine-readable audit record for every call. What this is The open-source core is rule-based. It does four things: recognizes known prompt-injection and jailbreak phrasings, de-obfuscates common evasions (zero-width characters, homoglyphs, leetspeak, letter-spacing, base64) so those known phrasings still match after they have been disguised, scans retrieved context and tool output for the same patterns before they reach the model (indirect injecti…
推荐参考
信息
- 协议
- Apache-2.0
- 语言
- Python
- GitHub 星标
- 14
- 月下载
- –
- 最近更新
- 2026-09-23
- 创建于
- 2026-05-29
基础安全检查
- 检查结果
- curated 收录但无 npm 包/安装命令
- 收录来源
- curated:punkpeye/awesome-mcp-servers
- 主题标签
- ai-safety, explainable-ai, guardrails, jailbreak-detection, llm-guardrails, llm-security, owasp-llm, prompt-injection, python
同类推荐
langfuse
langfuse/langfuse
🪢 开源AI工程平台：LLM评估、可观测性、指标、提示管理、游乐场、数据集。与OpenTelemetry、LangChain、OpenAI SDK、LiteLLM等集成。🍊YC W23