Search

The quality gate for Agent Skills: spec validation, security checks, context analysis, and publish-ready reports.

Security gate for pi: permission modes, rules, bash analysis, and an AI classifier (Claude Code-style)

Secure .env file encryption for team collaboration — AES-256-GCM, zero config, works with npx

Evidence lab for agent skills: static checks, security scan, score, and verified badges for any SKILL.md

BYOCB ArbInjectionSkill - Smart contract vulnerability scanner for arbitrary call injection. Educational tool for security research.

Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes

VoltJS - Lightning-fast, batteries-included, security-first JavaScript framework. Zero boilerplate, maximum power.

A high-performance, multi-layer email trust engine for advanced validation, reputation scoring, and security analysis.

Pre-install security audit for Base-chain agent skills. Deterministic ALLOW/WARN/DENY verdict.

Universal code review skill for Claude Code and OpenCode AI agents - SOLID, security, performance analysis

SDK for connecting applications to Valence AI for security issues, runtime signals, and optional runtime review flows.

Easily generate RSA Public-Private Keypairs and use them for secure asymmetric one-way encryption and decryption!

QA + Security Scanner for vibe-coded applications. Your AI writes code. QASS catches what it got wrong.

Multi-agent security testing tool - Red Team vs Blue Team with Green Team referee

CLI to scan a repo and generate missing GitHub community health files (.github templates, CONTRIBUTING, SECURITY, etc.)

Fortify your vibe-coded app. Scan AI-built apps for security, test, deployment and data-safety gaps.

Zero-config security auditor and slopsquatting detector for Next.js, Supabase, Prisma, Stripe, Paystack, and PayPal stacks

🔒 Secure & modern Quill.js module for resizing images, videos, and iframes with zero vulnerabilities and automatic releases

Open Agent Security Benchmark — 222 attack scenarios mapped to MITRE ATLAS and OWASP Agentic Top 10

Self-hosted security layer for LLM applications — detect PII by format, substitute or mask, and audit every call.