Search
Middleware pipeline bridging sovereign-sensor raw intake and sovereign-ledger immutable storage via sovereign-sieve payload transformation
...moreTokenBreak Scanner Contributors
Detect TokenBreak adversarial vulnerabilities in LLMs, classifiers, and encoders. Audit HuggingFace tokenizer artifacts for BPE/WordPiece attack surface.
...morechispecial
A lightweight Web Authentication library supporting WebAuthn, password credentials, and biometric login for browsers.
Dmitry Krivonosov
Data-only defensive playbooks and canonical offline advisory policy pack.
kauaim
Free, open-source skills for Claude Code and Claude Desktop — starting with a prompt-injection guard for safely ingesting untrusted documents.
...moreComoco235
Pre-ship audit skill for SaaS that takes money. Finds the billing and data-isolation holes generic scanners miss on Next.js + Supabase + Stripe.
...moreEIP-712 typed signature phishing permit auditor & allowance sanitizer (Permit2 / MetaMask)
mateo89libra
Protect GraphQL APIs from deep and expensive queries using depth and complexity limits
sparklingideas
AI Manipulation Defense System (AIMDS) with self-learning, prompt injection detection, and vector search integration
lelu-auth
TypeScript SDK for Lelu — the authorization engine for autonomous AI agents
martinholovsky
State-of-the-Art (2026) AI/LLM engineering skills/agents for building and auditing software — 40+ domain & language skills, BUILD/AUDIT modes, audit checklists.
...moresaifaldin14
Agent Action Firewall — a deterministic gate that blocks the lethal trifecta by construction. A framework-agnostic TypeScript library that any agent runtime (OpenAI SDK, LangChain, custom loops) can wrap around its tool-calling layer.
...moreaiagentwithdhruv
Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.
...morex-glacier
AI agent skill for autonomous penetration testing via Kali Linux — 199 CLI tools, 15 scenario playbooks, depth-enforced workflows over SSH or Docker. Works with Claude Code, OpenClaw, and Hermes Agent.
...morejessety
Library designed to make building APIs that use HMAC signatures simple.
neretj
Open-source PII firewall for LLM apps. Detect, anonymize and rehydrate sensitive data before it reaches OpenAI, Anthropic or any LLM provider.
...moreComposio
Bitwarden is a secure password management solution providing encrypted vaults, cross-platform sync, and enterprise-grade security tools for storing and sharing credentials
...moreAlpha-Park
Sliding-window nonce ledger and replay attack detector invalidating duplicated agent API requests and token reflections.
Use Remy to discover and triage engineering plans automatically across your organization. This helps ensure early review coverage, which is critical in identifying risky plans before they can cause harm. The platform automates the initiation of reviews and sends dynamic kick-off questions to engineering teams, minimizing delays and enhancing communication. By providing full visibility of all engineering proposals and their potential risks, Remy helps organizations reduce cost, risk, and time ass
...more