| 1. | | Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks (arxiv.org) |
| 1 point by lbeurerkellner 4 days ago | past | 1 comment |
|
| 2. | | Snyk Agent Scan: Security scanner for AI agents, MCP servers and agent skills (github.com/snyk) |
| 2 points by lbeurerkellner 12 days ago | past | discuss |
|
| 3. | | MCP-Scan: A Security scanner for AI agents, MCP servers and agent skills (github.com/invariantlabs-ai) |
| 3 points by lbeurerkellner 33 days ago | past |
|
| 4. | | Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem (github.com/invariantlabs-ai) |
| 3 points by lbeurerkellner 33 days ago | past |
|
| 5. | | MCP-Scan: Constrain, log and scan your MCP server for security vulnerabilities (github.com/invariantlabs-ai) |
| 2 points by lbeurerkellner 4 months ago | past |
|
| 6. | | Exposing Novel Prompt Injections, "Toxic Flows" in Agentic Systems (invariantlabs.ai) |
| 1 point by lbeurerkellner 7 months ago | past |
|
| 7. | | Hardening AI Agent Security with Toxic Flow Analysis (invariantlabs.ai) |
| 2 points by lbeurerkellner 7 months ago | past |
|
| 8. | | Mcp-scan: constrain, log and scan your active MCP connections (github.com/invariantlabs-ai) |
| 1 point by lbeurerkellner 9 months ago | past |
|
| 9. | | mcp-scan: Constrain, log and scan MCP traffic for security vulnerabilities (github.com/invariantlabs-ai) |
| 2 points by lbeurerkellner 9 months ago | past |
|
| 10. | | MCP Streamable HTTP – Python and TypeScript Examples (github.com/invariantlabs-ai) |
| 2 points by lbeurerkellner 9 months ago | past |
|
| 11. | | Show HN: Guardrails – A Contextual Security Layer for Agentic AI Systems (invariantlabs.ai) |
| 1 point by lbeurerkellner 10 months ago | past |
|
| 12. | | Securing Agents with Rules (invariantlabs.ai) |
| 2 points by lbeurerkellner 10 months ago | past |
|
| 13. | | MCP-scan: A security scanning tool for MCP servers (github.com/invariantlabs-ai) |
| 1 point by lbeurerkellner 11 months ago | past |
|
| 14. | | AgentDojo: An Environment to Evaluate Prompt Injection Attacks on AI Agents (spylab.ai) |
| 3 points by lbeurerkellner 11 months ago | past |
|
| 15. | | WhatsApp MCP Exploited: Exfiltrating your message history via MCP (invariantlabs.ai) |
| 3 points by lbeurerkellner 11 months ago | past |
|
| 16. | | MCP Tool Poisoning: Taking over Your Favorite MCP Client (lbeurerkellner.github.io) |
| 2 points by lbeurerkellner 11 months ago | past |
|
| 17. | | MCP Tool Poisoning: Taking over Your Favorite MCP Client (lbeurerkellner.github.io) |
| 2 points by lbeurerkellner 11 months ago | past |
|
| 18. | | MCP is all fun, until you add this one malicious MCP server and forget about it (twitter.com/lbeurerkellner) |
| 1 point by lbeurerkellner 11 months ago | past |
|
| 19. | | MCP Tool Poisoning: Taking over Your Favorite MCP Client (lbeurerkellner.github.io) |
| 1 point by lbeurerkellner 11 months ago | past |
|
| 20. | | JSONSchemaBench: Generating Structured Outputs from Language Models (github.com/guidance-ai) |
| 1 point by lbeurerkellner on Feb 14, 2025 | past |
|
| 21. | | Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai) |
| 1 point by lbeurerkellner on Feb 11, 2025 | past |
|
| 22. | | Invariant: A security and bug scanner for agent traces (github.com/invariantlabs-ai) |
| 1 point by lbeurerkellner on Feb 7, 2025 | past |
|
| 23. | | Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai) |
| 1 point by lbeurerkellner on Jan 24, 2025 | past |
|
| 24. | | Security Scanner for AI Agent Traces: Invariant Analyzer (github.com/invariantlabs-ai) |
| 1 point by lbeurerkellner on Jan 23, 2025 | past |
|
| 25. | | playwright-computer-use: Let Claude control a web browser on your machine (github.com/invariantlabs-ai) |
| 3 points by lbeurerkellner on Jan 22, 2025 | past |
|
| 26. | | Invariant Agent Stack: A framework-less approach to robust agent development (github.com/invariantlabs-ai) |
| 1 point by lbeurerkellner on Jan 21, 2025 | past |
|
| 27. | | Show HN: Let Claude control a web browser on your machine (github.com/invariantlabs-ai) |
| 3 points by lbeurerkellner on Jan 21, 2025 | past |
|
| 28. | | Invariant Analyzer: Security scanner for AI agent trajectories (github.com/invariantlabs-ai) |
| 6 points by lbeurerkellner on Dec 30, 2024 | past |
|
| 29. | | Invariant Explorer: A tool for visualizing and exploring agent traces (github.com/invariantlabs-ai) |
| 1 point by lbeurerkellner on Dec 27, 2024 | past |
|
| 30. | | Show HN: Try test-driven agent development in this holiday prompting challenge (invariantlabs.ai) |
| 3 points by lbeurerkellner on Dec 23, 2024 | past |
|
|
| More |
