| | Exposing Novel Prompt Injections, "Toxic Flows" in Agentic Systems (invariantlabs.ai) |
| 1 point by lbeurerkellner 5 months ago | past |
|
| | Hardening AI Agent Security with Toxic Flow Analysis (invariantlabs.ai) |
| 2 points by lbeurerkellner 5 months ago | past |
|
| | New MCP Security Research and OSS Tooling: Toxic Flow Analysis (invariantlabs.ai) |
| 4 points by rdegges 5 months ago | past |
|
| | Accessing private GitHub repositories via MCP (invariantlabs.ai) |
| 110 points by gokhan 7 months ago | past | 1 comment |
|
| | GitHub MCP exploited: Accessing private repositories via MCP (invariantlabs.ai) |
| 508 points by andy99 7 months ago | past | 297 comments |
|
| | Show HN: Guardrails – A Contextual Security Layer for Agentic AI Systems (invariantlabs.ai) |
| 1 point by lbeurerkellner 8 months ago | past |
|
| | Securing Agents with Rules (invariantlabs.ai) |
| 2 points by lbeurerkellner 8 months ago | past |
|
| | MCP Security: Poisoning Agents (invariantlabs.ai) |
| 1 point by nesk_ 9 months ago | past |
|
| | WhatsApp MCP Exploited (invariantlabs.ai) |
| 25 points by typeofhuman 9 months ago | past | 1 comment |
|
| | WhatsApp MCP Exploited: Exfiltrating your message history via MCP (invariantlabs.ai) |
| 3 points by lbeurerkellner 9 months ago | past |
|
| | MCP Security Notification: Tool Poisoning Attacks (invariantlabs.ai) |
| 6 points by throwawai123 9 months ago | past |
|
| | MCP Tool Poisoning (invariantlabs.ai) |
| 2 points by vibe_ninjai 9 months ago | past |
|
| | MCP Security Notification: Tool Poisoning Attacks (invariantlabs.ai) |
| 1 point by ghuntley 9 months ago | past |
|
| | MCP Security Notification: Tool Poisoning Attacks (invariantlabs.ai) |
| 4 points by marcfisc 9 months ago | past |
|
| | Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai) |
| 1 point by lbeurerkellner 11 months ago | past |
|
| | Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai) |
| 1 point by lbeurerkellner 11 months ago | past |
|
| | Show HN: Try test-driven agent development in this holiday prompting challenge (invariantlabs.ai) |
| 3 points by lbeurerkellner on Dec 23, 2024 | past |
|
| | Show HN: A registry of agent benchmarks (including many OSS agent trajectories) (invariantlabs.ai) |
| 6 points by lbeurerkellner on Dec 23, 2024 | past | 1 comment |
|
| | Releasing Explorer and Testing: Visualize and Understand AI Agents (invariantlabs.ai) |
| 1 point by lbeurerkellner on Dec 19, 2024 | past |
|
| | Invariant Benchmark Registry: Understanding Agentic Intelligence (invariantlabs.ai) |
| 1 point by lbeurerkellner on Dec 13, 2024 | past |
|
| | Understanding Agentic Intelligence: Inspecting runtime traces of actual agents (invariantlabs.ai) |
| 1 point by lbeurerkellner on Nov 28, 2024 | past |
|
| | Show HN: Agent Benchmark Repository and Viewer (invariantlabs.ai) |
| 2 points by marcfisc on Nov 26, 2024 | past |
|
| | Invariant CTF 24: Fool an AI Agent to Extract the Secret Password (invariantlabs.ai) |
| 1 point by lbeurerkellner on Aug 20, 2024 | past |
|
| | AI CTF: Extracting Password from an AI Agent (invariantlabs.ai) |
| 1 point by bmislav on Aug 12, 2024 | past |
|
| | Invariant CTF: Fool an AI Agent to Extract the Secret Password (invariantlabs.ai) |
| 4 points by lbeurerkellner on Aug 5, 2024 | past |
|
| | What we've learned from analyzing hundreds of AI web agent traces (invariantlabs.ai) |
| 2 points by bmislav on July 17, 2024 | past |
|
