HNHacker News
TopNewBestAskShowJobs

edf13

1,507 karma · joined October 20, 2017

hello at fieldlogic.uk
submissionscomments

Show HN: ClaudeStatsBar: your session is 486k deep and nothing told you

github.com·18 pts·edf13·
15

A Git Config Key Ran Code in Seven Coding Agents. The 2022 Fix Does Not Stop It

grith.ai·4 pts·edf13·
0

Show HN: Grith – syscall-level supervision for AI agents

github.com·3 pts·edf13·
1

An agent skill can hand a stranger your shell – hours after you installed it

grith.ai·3 pts·edf13·
0

98% of What Claude Code Does, I Never See. The 0.27% It Stops for Is the Point

grith.ai·1 pts·edf13·
0

73% of What We Blocked in a Month Was One Syscall Your Sandbox Cannot See

grith.ai·3 pts·edf13·
0

Grith is live – security proxy for AI coding agents

grith.ai·4 pts·edf13·
1

Show HN: Grith – syscall-level supervision for AI coding agents on Linux

github.com·4 pts·edf13·
0

Wait – is this even Codex, or is it malware?

grith.ai·2 pts·edf13·
0

Codex swept my whole disk for credentials. grith froze every real one

grith.ai·5 pts·edf13·
0

An AI Model Escaped Its Eval and Breached Hugging Face. Every Step Was a Syscall

grith.ai·4 pts·edf13·
0

Mythos Proves AI Safety Can No Longer Live Inside the Model

grith.ai·2 pts·edf13·
0

Mythos Proves AI Safety Can No Longer Live Inside the Model

grith.ai·3 pts·edf13·
0

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

grith.ai·2 pts·edf13·
0

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

grith.ai·3 pts·edf13·
2

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

grith.ai·2 pts·edf13·
0

Vibe Coding Still Needs a Senior Engineer (For Now)

grith.ai·5 pts·edf13·
1

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

grith.ai·3 pts·edf13·
1

The Vercel Breach Needed Malware. The Next One Needs a Bad Readme

grith.ai·1 pts·edf13·
3

Every Claude 4.7 Improvement Makes the Security Problem Worse

grith.ai·5 pts·edf13·
1

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

grith.ai·4 pts·edf13·
0

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

grith.ai·3 pts·edf13·
0

Prompt Injection Is Unfixable (So We Stopped Trying)

grith.ai·4 pts·edf13·
1

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

grith.ai·5 pts·edf13·
0

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

grith.ai·3 pts·edf13·
0

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

grith.ai·3 pts·edf13·
0

Claude now decides what's safe to run – a UX improvement, not a security fix

twitter.com·3 pts·edf13·
0

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

grith.ai·3 pts·edf13·
0

The Trivy Supply Chain Attack Reached LiteLLM

grith.ai·3 pts·edf13·
1

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

grith.ai·1 pts·edf13·
0
Page 1 of 6Next →