| OWASP AI Agent Security Cheat Sheet | Frameworks and Standards | OWASP |
| HashiCorp comment on NIST AI Agent Security RFI - Agentic Runtime Security | Governance and Policy | AI Policy |
| 🌟 Open Source AI Agent Security Infrast | Agent Security | Agent Security Frameworks and Tools |
| Give your AI agent instant API loo | Agent Security | Agent Security Frameworks and Tools |
| How AI Agents Automate CVE Vulnerability Research | Agent Security | Agent Security Frameworks and Tools |
| SCAM — How safe is your AI agent? | Agent Security | Agent Security Frameworks and Tools |
| SuperClaw: Red-Team AI Agents Be | Agent Security | Agent Security Frameworks and Tools |
| Every API key you paste into an AI agent's input box hits | Agent Security | Agent Security Frameworks and Tools |
| AI Agent Lands PRs in Major OSS Projects, Targets Maintainer | Agent Security | Agent Security Frameworks and Tools |
| Agentic SOC Platform: A po | Agent Security | Agent Security Frameworks and Tools |
| An AI-powered agentic red team framewor | Agent Security | Agent Security Frameworks and Tools |
| NeuralTrust - The Platform for AI and Agent Security | Agent Security | Agent Security Frameworks and Tools |
| Supply-chain risk of agentic AI - infecting infrastructures via ski | Agent Security | Agent Security Frameworks and Tools |
| 'Signal' President and VP warn agentic AI is insecure, unreliable, | Agent Security | Agent Security Frameworks and Tools |
| Never Trust the Output: Data Pollution in AI Agents and MCP | Agent Security | Agent Security Frameworks and Tools |
| Runtime enforcement layer for AI agent a | Agent Security | Agent Security Frameworks and Tools |
| A curated list of 150+ pa | Agent Security | Agent Security Frameworks and Tools |
| Open-source AI agents for penetration testing | Agent Security | Agent Security Frameworks and Tools |
| Block, Anthropic, and OpenAI Launch the Agentic AI Foundation | Agent Security | Agent Security Frameworks and Tools |
| Linux Foundation Announces the Formation of the Agentic AI Foundati | Agent Security | Agent Security Frameworks and Tools |
| 🔐Secure AI Agent Knowledge Retrieval - Introducing Security Filt | Agent Security | Agent Security Frameworks and Tools |
| How Code Execution Drives Key Risks in Agentic AI Systems - NVIDIA | Agent Security | Agent Security Frameworks and Tools |
| Autofix Bot: AI Agent purpose-built for code security - Autofix Bot | Agent Security | Agent Security Frameworks and Tools |
| Introducing Aardvark: OpenAI's agentic security researcher | Agent Security | Agent Security Frameworks and Tools |
| Leash by StrongDM — Security for AI Agents | Agent Security | Agent Security Frameworks and Tools |
| securing ai agents.pptx | Agent Security | Agent Security Frameworks and Tools |
| Agentic AI Red Teaming Playbook | Agent Security | Agent Security Frameworks and Tools |
| AI agent for autonomous cyber | Agent Security | Agent Security Frameworks and Tools |
| Google DeepMind introduces new AI agent for code security | Agent Security | Agent Security Frameworks and Tools |
| Agentic AI Threat Modeling Framework: MAESTRO - CSA | Agent Security | Agent Security Frameworks and Tools |
| MAESTRO: Streamlining Agentic AI Security in IriusRisk | Agent Security | Agent Security Frameworks and Tools |
| Agentic Misalignment: How LLMs could be insider threats | Agent Security | Agent Security Frameworks and Tools |
| The lethal trifecta for AI agents: private data, untrusted content, | Agent Security | Agent Security Frameworks and Tools |
| Unit 42 Develops Agentic AI Attack Framework | Agent Security | Agent Security Frameworks and Tools |
| How to Hack AI Agents and Applications | Agent Security | Agent Security Frameworks and Tools |
| A security scanner for your LLM age | Agent Security | Agent Security Frameworks and Tools |
| A Dynamic Environment to Evaluate A | Agent Security | Agent Security Frameworks and Tools |
| Shinobi Security - Uncloud the cloud with your personal AI detective | Agent Security | Agent Security Frameworks and Tools |
| A curated list of GPT agents f | Agent Security | Agent Security Frameworks and Tools |
| AARTS: An Open Standard for AI Agent Runtime Safety | Agent Security | Agent Security Frameworks and Tools |
| Run NanoClaw in Docker Sandboxes with One Command | Agent Security | Agent Security Frameworks and Tools |
| Agent Governance Toolkit: Application-level security middleware for autonomous AI agents | Agent Security | Agent Security Frameworks and Tools |
| OpenShell - Safe, Private Runtime for Autonomous AI Agents | Agent Security | Agent Security Frameworks and Tools |
| Skills Security Index - Security Risk Analysis for Agentic AI Skill Definitions | Agent Security | Agent Security Frameworks and Tools |
| NemoClaw - Open Source Stack for Running OpenClaw Agents Safely | Agent Security | Agent Security Frameworks and Tools |
| OneCLI - Secret Vault for AI Agents | Agent Security | Agent Security Frameworks and Tools |
| openclaw-a365 - Native Microsoft 365 Channel for OpenClaw | Agent Security | Agent Security Frameworks and Tools |
| Agent skills to help with Continuous Threa | Agent Security | Agent Security Frameworks and Tools |
| Fully-Autonomous AI Systems Are Discovering Vulns Today | Agent Security | Agent Security Frameworks and Tools |
| Streamlining Security Investigations with Agents | Agent Security | Agent Security Frameworks and Tools |
| Agents testing framework made easy | Agent Security | Agent Security Frameworks and Tools |
| XBOW – Agents Built From Alloys | Agent Security | Agent Security Frameworks and Tools |
| Charlemagne Labs - Safety is a Human Right | Agent Security | Agent Security Frameworks and Tools |
| Clopus-Watcher: "intelligent" monitoring | Agent Security | Agent Security Frameworks and Tools |
| AI Agent Benchmarks are Broken | Agent Security | Agent Security Frameworks and Tools |
| Introducing tapes: transparent AI agent telemetry | Agent Security | Agent Security Frameworks and Tools |
| Repo for "Adaptat | Agent Security | Agent Security Frameworks and Tools |
| State of Agentic AI: Founder's edition - MMC | Agent Security | Agent Security Frameworks and Tools |
| Cursor "Open-Folder" Autorun Vulnerability Exposes Developers t | Agent Security | Agent Security Frameworks and Tools |
| Anthropic faces backlash to Claude 4 Opus behavior that contacts au | Agent Security | Agent Security Frameworks and Tools |
| Wow\. Opus 4\.6 aggressively acquired and used authentication tokens and took unapproved | Agent Security | Agent Security Frameworks and Tools |
| The Agent Perimeter Fallacy | Agent Security | Agent Security Frameworks and Tools |
| AARM - Autonomous Action Runtime Management, runtime security standard for AI agents | Agent Security | Agent Security Frameworks and Tools |
| ADR - Agentic AI Detection and Response, deployed at Uber | Agent Security | Agent Security Frameworks and Tools |
| Adrian - open-source runtime AI agent security monitor | Agent Security | Agent Security Frameworks and Tools |
| Agent Baseline - six security outcomes for enterprise AI agents | Agent Security | Agent Security Frameworks and Tools |
| agentseal - security toolkit for AI agents, scans skills and MCP configs, tests prompt injection | Agent Security | Agent Security Frameworks and Tools |
| AI agent shared responsibility model - Microsoft Azure | Agent Security | Agent Security Frameworks and Tools |
| Alex Volkov on NVIDIA announcing NemoClaw, a secure enterprise OpenClaw platform at GTC | Agent Security | Agent Security Frameworks and Tools |
| ATR - Agent Threat Rules detection rule database | Agent Security | Agent Security Frameworks and Tools |
| AVE - Behavioral Classification Standard for Agentic AI | Agent Security | Agent Security Frameworks and Tools |
| Clawdstrike - agentic AI EDR for developer workstations and agent swarms | Agent Security | Agent Security Frameworks and Tools |
| ClawSec - security skill suite for AI agents | Agent Security | Agent Security Frameworks and Tools |
| ClawVault - OpenClaw security vault controlling agent access to secrets and data | Agent Security | Agent Security Frameworks and Tools |
| Cloudflare Mesh - secure private networking for users, nodes, and AI agents | Agent Security | Agent Security Frameworks and Tools |
| DefenseClaw - security governance for OpenClaw and agentic AI runtimes | Agent Security | Agent Security Frameworks and Tools |
| enforra - open source action governance SDK for AI agent tool calls | Agent Security | Agent Security Frameworks and Tools |
| Geordie AI - AI agent governance, observability and control platform | Agent Security | Agent Security Frameworks and Tools |
| h5i - secure, auditable browser for AI agents | Agent Security | Agent Security Frameworks and Tools |
| Introducing Prempti: Falco meets AI coding agents | Agent Security | Agent Security Frameworks and Tools |
| Introducing RAMPART and Clarity: Open Source Tools for Agent Development Safety | Agent Security | Agent Security Frameworks and Tools |
| iron-sensor - eBPF behavioral monitor for AI coding agents | Agent Security | Agent Security Frameworks and Tools |
| Kim Maida - The Agent Security Stack: Transport, Identity, Policy, Runtime | Agent Security | Agent Security Frameworks and Tools |
| Microsoft Agent Governance Toolkit - OpenClaw sidecar deployment guide | Agent Security | Agent Security Frameworks and Tools |
| microsoft/fides - Securing AI agents with information-flow control | Agent Security | Agent Security Frameworks and Tools |
| microsoft/fides tutorial - securing AI agents with information-flow control | Agent Security | Agent Security Frameworks and Tools |
| OpenClaw Security Platform - bring-your-own-security for AI agents | Agent Security | Agent Security Frameworks and Tools |
| OpenClaw Security Platform - security layer for AI agents | Agent Security | Agent Security Frameworks and Tools |
| Pedro Franceschi on CrabTrap - an LLM-as-a-judge HTTP proxy to secure agents in production | Agent Security | Agent Security Frameworks and Tools |
| Prismor - AI agent security control plane | Agent Security | Agent Security Frameworks and Tools |
| SAM - Sovereign Agent Mesh, zero-trust P2P network for AI agents | Agent Security | Agent Security Frameworks and Tools |
| Securing Agents Across Perplexity's Client Endpoints with Numbat | Agent Security | Agent Security Frameworks and Tools |
| sentra - external security provider for Microsoft Copilot Studio | Agent Security | Agent Security Frameworks and Tools |
| SlowMist Agent Security Skill - security review framework for AI agents | Agent Security | Agent Security Frameworks and Tools |
| Straiker - the agentic AI security company | Agent Security | Agent Security Frameworks and Tools |
| sycophant - zero-trust framework for autonomous AI agents | Agent Security | Agent Security Frameworks and Tools |
| tailcat - netcat-style encrypted tunnels from Tailscale for ad-hoc access without accounts or tailnets | Agent Security | Agent Security Frameworks and Tools |
| tirith - terminal security for developers and AI agents | Agent Security | Agent Security Frameworks and Tools |
| Trusted Remote Execution - policy-enforced scripts for AI agents | Agent Security | Agent Security Frameworks and Tools |
| Uber open-sources ADR - Agentic Detection and Response framework and ADR-Bench | Agent Security | Agent Security Frameworks and Tools |
| xaidr - runtime security for AI agents | Agent Security | Agent Security Frameworks and Tools |
| XBOW on how its autonomous offensive security agent architecture prevents OpenAI-Hugging Face style incidents | Agent Security | Agent Security Frameworks and Tools |
| Your AI Agent Is Indistinguishable From Malware | Agent Security | Agent Security Frameworks and Tools |
| Zero Trust for AI Agents - A security framework for deploying autonomous AI agents in the enterprise | Agent Security | Agent Security Frameworks and Tools |
| AI Agent Smart Contract Exploit Generation | Agent Security | Research |
| Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks | Agent Security | Research |
| Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study | Agent Security | Research |
| SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement | Agent Security | Research |
| Agents of Chaos | Agent Security | Research |
| AI Agents Enable Adaptive Computer Worms | Agent Security | Research |
| Browser AI Agents: The New 'Weakest Link' that Can Feed Your Credentials and Data to Attackers | Agent Security | Research |
| Emergent Cyber Behavior: When AI Agents Become Offensive Threat Actors | Agent Security | Research |
| endpoint-ai-agent-abuse - catalog of local AI agent abuse techniques | Agent Security | Research |
| GPT-5.5-Cyber built a zlib fuzzing lab in a day | Agent Security | Research |
| Meta - Practical AI Agent Security | Agent Security | Research |
| OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage | Agent Security | Research |
| Patterns and problems in multiagent systems - Anthropic on coordination failures, collusion and sabotage | Agent Security | Research |
| Prelude shows Claude Code reading the macOS iMessage database despite EDR | Agent Security | Research |
| Prismor - measuring secret exposure across 10,000 Claude Code agent sessions | Agent Security | Research |
| Watching Agents Work: A Behavioral Audit of Offensive-Security LLM Runs | Agent Security | Research |
| When an Attacker Meets a Group of Agents: Navigating Amazon Bedrock's Multi-Agent Applications | Agent Security | Research |
| A Comparative Evaluation of AI Agent Security Guardrails | Papers | Defense and Detection |