Search

A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on modern AI technologies like Large Language Models (LLMs), Agents, and Multi-Modal systems and their applications in security operations.

Controlled Web AI Agent V2 — A Python tool-calling AI agent for web research, website security analysis, file management, and approved terminal commands, with built-in SSRF protection, domain locking, human approval gates, and safety controls.

ESLint plugin for OpenAI SDK security — catches dangerouslyAllowBrowser, which ships your API key to every visitor.

Policy evaluation engine for Aegisora AI governance runtime.

A curated list of tools, research, standards and datasets for the security of AI agent extensions — skills, MCP servers, plugins and rules files.

Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vulns, not you.

Agent Memory Integrity (agmi): a conformance test suite that measures whether AI agent memory and checkpoint stores notice tampering

Local-first security scanner and integrity monitor for OpenClaw skills.

Offensive security testing for AI agents

Comprehensive AI Agent Security Platform - scan, monitor, and secure AI CLI configurations with IDE integrations, behavior analysis, and compliance frameworks

Security-first AI agent orchestration system. Built-in agents with predefined capabilities, strict guardrails on what they can and cannot do, and a four-layer defense system that enforces security at every stage of the message lifecycle.

Declarative guardrails and safety controls for .NET AI agents

LangChain governance middleware for Aegis ACP

AWS Bedrock Agents governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

Discover and inventory autonomous AI agents across your infrastructure - static analysis, runtime detection, and Kubernetes monitoring

The dashcam and emergency brake for AI agents. A security proxy that physically blocks rogue LLM commands and generates cryptographically proven audit trails for enterprise compliance.

Deterministic security scanner for AI agent skills + Trusted Distribution CLI. Local, zero-dependency, executes nothing. Facts, not verdicts.

Audit LLM API routers for tool-call tampering, credential exfiltration and supply-chain risk

Local-first runtime controls for Python LLM apps and agents: budget circuit breakers, PII/secrets redaction, tool-call policy checks, rate limits, and audit traces — in 2 lines, no hosted proxy.

DeepSeek Harness plugin that blocks risky npm installs with metadata and deep supply-chain scans