Flagged: environment access. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by CassiopeiaCode · LLM Plugin · ★ 83
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is CosyRedactGateway safe to install? View the security audit →
Cosy Redact Gateway 高熵凭据检测：不只匹配已知密钥，也检查没有固定格式的随机凭据。 High-entropy credential detection — beyond known key formats. 简体中文 · English 高熵检测 · 本地全开 · 验证 · 接入 · 安全边界 凭据不一定以 开头。一个内部服务令牌，可能只是代码、配置、日志或工具结果里的一串随机字符。 Cosy 是面向程序员的 LLM 凭据脱敏网关，核心是高熵凭据检测（High-entropy credential detection）。 它不仅匹配已知密钥格式，还对符合条件的文本块进行统计评分，寻找随机形态的凭据候选，不要求厂商前缀，也不要求 这样的赋值标签。 全部检测器启用时，高熵检测与结构化检测、Gitleaks 兼容密钥规则协同工作：命中内容在转发前替换为可逆占位符，并在普通响应、受支持的 SSE 流和工具调用参数中还原已知、未被修改的占位符。高熵检测对应配置开关 。 面向程序员的本地优先用法：把 Cosy 跑在本机，让受支持的 LLM 调用经过它。 下方示例统一使用 ，启用全部检测器。 保护范围： 检查经过网关的 JSON 文本，并替换命中
| Stars | 83 |
| Forks | 18 |
| Language | JavaScript |
| Category | LLM Plugin |
| License | Apache-2.0 |
| Quality Score | 62.227245151416/100 |
| Last Updated | 2026-09-18 |
| Created | 2026-09-11 |
| Platforms | node |
| Est. Tokens | ~16k |
These tools work well together with CosyRedactGateway for enhanced workflows:
Looking for a CosyRedactGateway alternative? If you're comparing CosyRedactGateway with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
数据面具 Data Maskit — 专为大模型打造的本地隐私脱敏网关（请求自动打码，回复流式还原；支持 Cursor / Claude Code / Codex / Pi 等任意可配 Base URL 工具）
Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more
OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch).
Intelligent Cost-Optimizing Model Router for OpenClaw
Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premi
Explore other popular llm plugin tools:
CosyRedactGateway is Lightweight, stateless privacy gateway for LLM APIs — redact secrets before OpenAI/Anthropic upstreams and restore them transparently in SSE and tool calls.. It is categorized as a LLM Plugin with 83 GitHub stars.
CosyRedactGateway is primarily written in JavaScript. It covers topics such as anthropic, cloudflare-workers, data-masking.
You can find installation instructions and usage details in the CosyRedactGateway GitHub repository at github.com/CassiopeiaCode/CosyRedactGateway. The project has 83 stars and 18 forks, indicating an active community.
CosyRedactGateway is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to CosyRedactGateway on Agent Skills Hub include maskit, NoPII, lm-proxy. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: