Search: invariantlabs.ai | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: A registry of agent benchmarks (including many OSS agent trajectories) (explorer.invariantlabs.ai)

6 points

a year ago

2.

Show HN: A CTF challenge that let's you attack an LLM-based agent

5 points

2 years ago

3.

Show HN: Guardrails – A Contextual Security Layer for Agentic AI Systems (invariantlabs.ai)

1 point

a year ago

4.

GitHub MCP exploited: Accessing private repositories via MCP (invariantlabs.ai)

508 points

a year ago

5.

Accessing private GitHub repositories via MCP (invariantlabs.ai)

110 points

a year ago

6.

WhatsApp MCP Exploited (invariantlabs.ai)

25 points

a year ago

7.

MCP Security Notification: Tool Poisoning Attacks (invariantlabs.ai)

6 points

a year ago

8.

New MCP Security Research and OSS Tooling: Toxic Flow Analysis (invariantlabs.ai)

4 points

10 months ago

9.

MCP Security Notification: Tool Poisoning Attacks (invariantlabs.ai)

4 points

a year ago

10.

Invariant CTF: Fool an AI Agent to Extract the Secret Password (invariantlabs.ai)

4 points

2 years ago

11.

WhatsApp MCP Exploited: Exfiltrating your message history via MCP (invariantlabs.ai)

3 points

a year ago

12.

Show HN: Try test-driven agent development in this holiday prompting challenge (invariantlabs.ai)

3 points

a year ago

13.

Hardening AI Agent Security with Toxic Flow Analysis (invariantlabs.ai)

2 points

10 months ago

14.

Securing Agents with Rules (explorer.invariantlabs.ai)

2 points

a year ago

15.

MCP Tool Poisoning (invariantlabs.ai)

2 points

a year ago

16.

Show HN: Agent Benchmark Repository and Viewer (explorer.invariantlabs.ai)

2 points

2 years ago

17.

What we've learned from analyzing hundreds of AI web agent traces (invariantlabs.ai)

2 points

2 years ago

18.

Exposing Novel Prompt Injections, "Toxic Flows" in Agentic Systems (invariantlabs.ai)

1 point

10 months ago

19.

MCP Security: Poisoning Agents (invariantlabs.ai)

1 point

a year ago

20.

MCP Security Notification: Tool Poisoning Attacks (invariantlabs.ai)

1 point

a year ago

21.

Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai)

1 point

a year ago

22.

Enhancing Browser Agent Safety with Guardrails (invariantlabs.ai)

1 point

a year ago

23.

Releasing Explorer and Testing: Visualize and Understand AI Agents (invariantlabs.ai)

1 point

a year ago

24.

Invariant Benchmark Registry: Understanding Agentic Intelligence (explorer.invariantlabs.ai)

1 point

a year ago

25.

Understanding Agentic Intelligence: Inspecting runtime traces of actual agents (explorer.invariantlabs.ai)

1 point

2 years ago

26.

Invariant CTF 24: Fool an AI Agent to Extract the Secret Password (invariantlabs.ai)

1 point

2 years ago

27.

AI CTF: Extracting Password from an AI Agent (invariantlabs.ai)

1 point

2 years ago