HN Explorer

lbeurerkellner

↗ HN profile [ 105 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. How We Evaluate Model Risk (research.snyk.io)
    1 points 0
  2. Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks (arxiv.org)
    1 points 1
  3. Snyk Agent Scan: Security scanner for AI agents, MCP servers and agent skills (github.com)
    2 points 0
  4. MCP-Scan: A Security scanner for AI agents, MCP servers and agent skills (github.com)
    3 points 0
  5. Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem (github.com)
    3 points 0
  6. MCP-Scan: Constrain, log and scan your MCP server for security vulnerabilities (github.com)
    2 points 0
  7. Exposing Novel Prompt Injections, "Toxic Flows" in Agentic Systems (invariantlabs.ai)
    1 points 0
  8. Hardening AI Agent Security with Toxic Flow Analysis (invariantlabs.ai)
    2 points 0
  9. Mcp-scan: constrain, log and scan your active MCP connections (github.com)
    1 points 0
  10. mcp-scan: Constrain, log and scan MCP traffic for security vulnerabilities (github.com)
    2 points 0
  11. MCP Streamable HTTP – Python and TypeScript Examples (github.com)
    2 points 0
  12. Show HN: Guardrails – A Contextual Security Layer for Agentic AI Systems (invariantlabs.ai)

    Hey HN, we are a small team from Europe building in agent security and we have just released Invariant Guardrails, our open-source system to enforce contextual security in AI agents and MCP-powered applications.…

    1 points 0
  13. Securing Agents with Rules (explorer.invariantlabs.ai)
    2 points 0
  14. MCP-scan: A security scanning tool for MCP servers (github.com)
    1 points 0
  15. AgentDojo: An Environment to Evaluate Prompt Injection Attacks on AI Agents (agentdojo.spylab.ai)
    3 points 0
  16. WhatsApp MCP Exploited: Exfiltrating your message history via MCP (invariantlabs.ai)
    3 points 0
  17. MCP Tool Poisoning: Taking over Your Favorite MCP Client (lbeurerkellner.github.io)
    2 points 0
  18. MCP Tool Poisoning: Taking over Your Favorite MCP Client (lbeurerkellner.github.io)
    2 points 0
  19. MCP is all fun, until you add this one malicious MCP server and forget about it (twitter.com)
    1 points 0
  20. MCP Tool Poisoning: Taking over Your Favorite MCP Client (lbeurerkellner.github.io)
    1 points 0
  21. JSONSchemaBench: Generating Structured Outputs from Language Models (github.com)
    1 points 0
  22. Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai)
    1 points 0
  23. Invariant: A security and bug scanner for agent traces (github.com)
    1 points 0
  24. Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai)
    1 points 0
  25. Security Scanner for AI Agent Traces: Invariant Analyzer (github.com)
    1 points 0