Search

MCP & SKILL scanner that scans any mcp server or skills for indirect attack vectors and security or configuration vulnerabilities. Aligned with OWASP SKILL Top 10 and OWASP MCP Top 10 threats & vulnerabilities.

TollWarden payment security for LangChain/LangGraph agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection, guard payment tools so blocked payments can never execute.

AI coding agent powered by DeepSeek via browser automation — no API key needed. Performance-optimized (30-40% faster). New --headless parameter for interactive mode. Enhanced with comprehensive security.

Epistemic dataset generation engine. 38 AI agents deliberate through multi-round Geth Consensus — producing auditable reasoning traces for AI training. Parliament System, Knowledge Grounding, zero-trust security.

LLM Guard Rails - An actively maintained security toolkit for Large Language Model interactions. Features advanced sanitization, harmful language detection, data leakage prevention, and prompt injection resistance with continuous improvements and enhancements.

PaySafe payment security for CrewAI agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection via a tool-call hook, and guard payment tools so blocked payments can never execute.

Mizan — an AI triage agent for security vulnerability reports, built on Meta's models. Reads reports and code, flags prompt-injection attempts, verifies claims by reasoning only (never executes anything), and proposes a decision for human review.

Security scanner for MCP server configurations. Like npm audit, but for your AI agent tool servers. Finds risky tools, input validation gaps, transport vulnerabilities, and over-permissioned capability chains. Open source, zero dependencies.

Your personal cybersecurity engineer for the age of AI. Free, open-source Mac security agent that works with your own AI or one running fully on your Mac. Watches AI agents, scams and malware, and changes nothing without your Touch ID.

TollWarden payment security for CrewAI agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection via a tool-call hook, and guard payment tools so blocked payments can never execute.

AI Agent Security Posture Scanner — enumerate all AI coding agents on a machine, map aggregate permissions, MCP servers, credential exposure. Scans Claude, Cursor, VS Code, Windsurf, Zed, Codex, aider, Moltbot.

Security enforcement layer for AI coding agents (Claude Code, Cursor, OpenAI Codex, custom runtimes). Blocks dangerous commands, audits every tool call, detects prompt injection. Usable as a CLI, a Node library, or a plugin.

Production-ready evaluation framework for AI agents — 58 metrics (25 native + 33 Harness Config) across 7 evaluation gates: goal achievement, behavioral integrity, reliability, performance, security, multi-agent coordination, and observability

ASHA developer preview (0.4.2): mission-aware Superintelligence (SI) agent governance (ANCHOR) plus drop-in LLM security and optimization. pip install asha-si (import asha). No API key or model download required.

Sorkcloud CLI — AI-powered security pipeline for Node.js projects. Scans, triages, fixes, verifies, and supports multiple AI agents (Claude, OpenAI, Codex, Gemini, Mistral, Llama). Works with BYOK or sorkcloud.space-managed keys.

Security observability + real-time policy enforcement for AI agents. Local-first NDJSON capture, Shield CLI that blocks policy violations live (with policies pulled from Fortress cloud), anonymizer producing signals-only payloads, and bidirectional sync w

Open source AI-powered penetration testing orchestrator that automates reconnaissance, vulnerability discovery, and analysis. Executes authorized security tests using installed tools, maintains immutable audit trails, and delivers findings with OWASP mapping and remediation guidance.

Enterprise-grade agentic AI framework. 8 LLM backends, declarative security policies, audit trails, SSRF protection, credential redaction, local GPU inference on NVIDIA Blackwell, Telegram/Discord/WhatsApp/Email channels, 16 autonomous observers.

WP-Hunter is a WordPress plugin/theme reconnaissance and static analysis (SAST) tool. It is designed for security researchers to evaluate the vulnerability probability of plugins by analyzing metadata, installation patterns, update histories, and performing deep Semgrep-powered source code analysis.

Pluggable component-based agent framework: modular architecture layers with address functions, np() single-call startup, 9 layers / 29 hooks, norpagent.safe() decoupled security, process-level plugin isolation, ready-to-use preset modes