Stories by lbeurerkellner

MCP-Scan: A Security scanner for AI agents, MCP servers and agent skills

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

MCP-Scan: Constrain, log and scan your MCP server for security vulnerabilities

Exposing Novel Prompt Injections, "Toxic Flows" in Agentic Systems

Hardening AI Agent Security with Toxic Flow Analysis

Mcp-scan: constrain, log and scan your active MCP connections

mcp-scan: Constrain, log and scan MCP traffic for security vulnerabilities

MCP Streamable HTTP – Python and TypeScript Examples

Show HN: Guardrails – A Contextual Security Layer for Agentic AI Systems

Securing Agents with Rules

MCP-scan: A security scanning tool for MCP servers

AgentDojo: An Environment to Evaluate Prompt Injection Attacks on AI Agents

WhatsApp MCP Exploited: Exfiltrating your message history via MCP

MCP Tool Poisoning: Taking over Your Favorite MCP Client

MCP Tool Poisoning: Taking over Your Favorite MCP Client

MCP is all fun, until you add this one malicious MCP server and forget about it

MCP Tool Poisoning: Taking over Your Favorite MCP Client

JSONSchemaBench: Generating Structured Outputs from Language Models

Enhancing Browser Agent Safety with Guardrails

Invariant: A security and bug scanner for agent traces

1