Permission modes and a shell safety floor for opencode: static read rules, credential guards, a classifier consulted only when nobody can be asked, loop detection and secret redaction.

AST-based shell safety guard for Claude Code, Codex, Grok Build, and Kimi Code

Bigmap for Keyv

A safe migration checker for Prisma.

A type-safe marriage of `EventTarget` and `EventEmitter`.

msgpack encoder and decoder in pure javascript based on creationix/msgpack-js updated to match the new v5 specification with string support.

Convert various schema validation libraries to JSON Schema

ContentSafety Service

Safe builders for Trusted Types values

Small module that makes sure your catch, caught an actual error and not a programming mistake or assertion

Openapi for zodios

Open source hooks library for AI coding agents - Install safety, quality, and automation hooks with a single command

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

A coding agent CLI hook - block destructive commands and secret file access

Native TUN/TAP interface module for Node.js

React client side library for [Reflag.com](https://reflag.com)

Vite Plugin for Angular

[ESLint formatter](https://eslint.org/docs/latest/extend/custom-formatters) that presents the results of @safety-web/eslint-plugin. This formatter only makes sense when @safety-web/eslint-plugin is also installed.

No description provided.

Legacy compatibility wrapper for SocialDataX / 社媒数据助手 Skills. New users should use socialdatax-skills.