Search: grith.ai | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

A GitHub Issue Title Compromised 4k Developer Machines

4 months ago

632 points

2.

A hidden prompt can steal your SSH keys

4 months ago

6 points

3.

87% of AI-Generated Pull Requests Ship Security Vulnerabilities

3 months ago

6 points

4.

Vibe Coding Still Needs a Senior Engineer (For Now)

a month ago

5 points

5.

Every Claude 4.7 Improvement Makes the Security Problem Worse

2 months ago

5 points

6.

If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised

3 months ago

5 points

7.

Vibe Coding Is Killing Open Source, and the Data Proves It

4 months ago

5 points

8.

Prompt Injection Is Unfixable (So We Stopped Trying)

2 months ago

4 points

9.

Google's A2A Protocol Has Zero Defenses Against Prompt Injection

3 months ago

4 points

10.

MCP Servers Are the New npm Packages

4 months ago

4 points

11.

They Hacked Claude, Gemini, and Copilot (and No One Told You)

2 months ago

4 points

12.

Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0

4 months ago

4 points

13.

AI Makes Adding Features Faster – So Why Not Add Just One More?

a month ago

3 points

14.

Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It

2 months ago

3 points

15.

The Trivy Supply Chain Attack Reached LiteLLM

3 months ago

3 points

16.

Permission Fatigue Is Not a UX Problem. It Is a Security Failure

3 months ago

3 points

17.

Mythos Proves AI Safety Can No Longer Live Inside the Model

12 days ago

3 points

18.

They Hacked Claude, Gemini, and Copilot (and No One Told You)

2 months ago

3 points

19.

Zero Ambient Authority: The Principle That Should Govern Every AI Agent

3 months ago

3 points

20.

Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels

3 months ago

3 points

21.

AI agents are now deciding what's safe to run (Claude Auto Mode)

3 months ago

3 points

22.

Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had

3 months ago

3 points

23.

NemoClaw vs. Grith: Sandbox for One Agent vs. Security for All

3 months ago

3 points

24.

Claude Code Auto Mode Lets the Agent Approve Its Actions – That's the Problem

3 months ago

3 points

25.

Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0

4 months ago

3 points

26.

AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension

3 months ago

2 points

27.

Mythos Proves AI Safety Can No Longer Live Inside the Model

10 days ago

2 points

28.

The Risk Isn't Rogue AI. It's Plausible AI

14 days ago

2 points

29.

AI Makes Adding Features Faster – So Why Not Add Just One More?

a month ago

2 points

30.

AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension

3 months ago

2 points