by CassiopeiaCode · LLM Plugin · ★ 105
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/CassiopeiaCode/CosyRedactGateway.gitTaken from the project's README on GitHub.
Flagged: environment access. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 105 |
| Forks | 24 |
| Language | JavaScript |
| Category | LLM Plugin |
| License | Apache-2.0 |
| Quality Score | 63/100 |
| Last Updated | 2026-10-31 |
| Created | 2026-09-11 |
| Platforms | node |
| Est. Tokens | ~16k |
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...
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）
Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code
Zero-dependency TypeScript secret and PII redaction for any SDK, logs, HTTP, LLM prompts, and scoped MCP tool
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
Explore other popular llm plugin tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: