Search
@espadalabs/action-firewall
saifaldin14
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.
...moresolongate-audit
codeyevsky
AI agent audit log tool — scans Claude Code, Gemini CLI & OpenClaw logs against OWASP Agentic Top 10
@stylusnexus/agentarmor-ml
stylusnexus
ML classifier add-on for Agent Armor. Downloads and runs a DeBERTa-v3-small ONNX model for agent trap detection.
Agent Attribution Practice
shimo4228
Architectural decision records on accountability distribution in autonomous AI agents — 10 ADRs + 4 Business AI Quadrants + Phase Separation axis. Harness-neutral practice library extracted from contemplative-agent. DOI on Zenodo.
...morepii-firewall
neretj
Open-source PII firewall for LLM apps. Detect, anonymize and rehydrate sensitive data before it reaches OpenAI, Anthropic or any LLM provider.
...moregiskard
Giskard AI <[email protected]>
The testing framework dedicated to ML models, from tabular to LLMs
raverse-mcp-server
use.manus.ai
MCP Server for RAVERSE - AI Multi-Agent Binary Patching System with 35 tools, NPX/NPM/PyPI support, and 20+ client configurations
...more@turtlepusher/browser
turtlepusher
Browser automation for AI agents - integrates agent-browser with cognition swarms
oors-security
viczam
oors security
acrf-mcp-scan
Ravi Karthick Sankara Narayanan, Kanna Sekar
MCP server inventory and risk scanner. Implements ACRF-03 defense pattern.
doctreen
candgrmc
Code-first API docs + OpenAPI 3.1 export + integration tests + runtime validation for Node.js. Define routes once with Zod and get docs, runnable flows, 422-on-invalid-request validation, OpenAPI 3.1 export, and schema drift detection for Express, Fastify
...moretokenbreak-scanner
TokenBreak Scanner Contributors
Detect TokenBreak adversarial vulnerabilities in LLMs, classifiers, and encoders. Audit HuggingFace tokenizer artifacts for BPE/WordPiece attack surface.
...moreGovernance
lua-ai-global
Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
...more@the-bot-club/agentguard
thebotclub
AgentGuard SDK — policy engine, audit trail, kill switch, and LangChain/OpenAI integrations
@enkryptai/clawpatrol
enkryptainpm
Guardrails and file integrity scanning for OpenClaw agents
agentguard-tech
AgentGuard — runtime governance for production AI agents. APRA CPS 230, EU AI Act and ISO 42001 evidence built-in. Native OpenClaw, LangChain, CrewAI, OpenAI Assistants, AutoGen, and MCP integrations.
...morepolkadot-secure-validator
fgimenez
[](https://circleci.com/gh/w3f/polkadot-secure-validator)
...moreMcp Security Audit
org_01KNB3BBYA74JHD0778KG97FBD
A powerful MCP (Model Context Protocol) Server that audits npm package dependencies for security vulnerabilities. Built with remote npm registry integration for real-time security checks.
...morereact-native-secure-sign
bartoszdadok
react-native-secure-sign lets you generates and use cryptographic signatures backed by hardware security on iOS and Android
...moremiddleBrick | API-Security
org_01KNBVXRGMV0T9Z12GX3NZJ4FT
Scan any API for OWASP Top 10 vulnerabilities and get a security risk score. Covers authentication, authorization (BOLA/BFLA), injection, data exposure, rate limiting, GraphQL, and LLM security.
...more