Search

Developer-first prompt-injection scanner for CI and local use

Production-ready Node.js + Express API boilerplate with JWT auth, RBAC, rate limiting, and database support (MongoDB/PostgreSQL)

Sandboxing shell for running AI coding agents inside Docker containers

Cashflows Client Library for JavaScript

Composable AI safety pipeline framework with industry compliance packs

AWS Encryption SDK implementation for Python

Protect your AI from Prompt Injection

Acquire AWS STS (temporary) credentials via Google Apps SAML Single Sign On

In-memory rate limiting for Node.js API routes with configurable windows and presets

Utility package to house all code that is not specific to prosopo. E.g. random number generation, string manipulation, etc.

Sanitize untrusted CSS with a configuration specified by a Whitelist. 根据白名单过滤CSS

Wizard CLI to set up and manage @claude-code-hooks packages for Claude Code.

SAFE test package: exfiltration-intent patterns with dummy data; localhost only; optional CLI.

Defend an agent against hidden-content injection: strip payload-capable invisible Unicode and ANSI, splice out human-invisible HTML, and flag data-exfil URLs in untrusted text before any model sees it.

User authentication management, including password, SMS, and support for Single Sign-On (SSO) protocols, with extensibility.

Access Mastercard APIs with OAuth 2.0 and FAPI 2.0

Defense-in-depth secret redaction OpenClaw plugin. Intercepts and irreversibly redacts secrets before any content reaches the LLM and sanitizes OpenClaw-owned transcripts/tool-result persistence.

A cache-based, IP blacklist for ExpressJS.

Rate limiting plugin for Harper applications

AI-powered secrets scanner for JavaScript/TypeScript. Detects and protects API keys, tokens, and credentials in source code and build artifacts. Features automatic fixing, built-in secrets manager, and zero-knowledge privacy. Superior alternative to gitle