edf13's submissions | Hacker News

1.		A Git Config Key Ran Code in Seven Coding Agents. The 2022 Fix Does Not Stop It (grith.ai)
		4 points by edf13 1 day ago \| past \| discuss
2.		Show HN: Grith – syscall-level supervision for AI agents (github.com/grith-ai)
		3 points by edf13 2 days ago \| past \| 1 comment
3.		An agent skill can hand a stranger your shell – hours after you installed it (grith.ai)
		3 points by edf13 3 days ago \| past \| discuss
4.		98% of What Claude Code Does, I Never See. The 0.27% It Stops for Is the Point (grith.ai)
		1 point by edf13 6 days ago \| past \| discuss
5.		73% of What We Blocked in a Month Was One Syscall Your Sandbox Cannot See (grith.ai)
		3 points by edf13 7 days ago \| past \| discuss
6.		Grith is live – security proxy for AI coding agents (grith.ai)
		4 points by edf13 13 days ago \| past \| 1 comment
7.		Show HN: Grith – syscall-level supervision for AI coding agents on Linux (github.com/grith-ai)
		4 points by edf13 13 days ago \| past \| discuss
8.		Wait – is this even Codex, or is it malware? (grith.ai)
		2 points by edf13 48 days ago \| past
9.		Codex swept my whole disk for credentials. grith froze every real one (grith.ai)
		5 points by edf13 48 days ago \| past
10.		An AI Model Escaped Its Eval and Breached Hugging Face. Every Step Was a Syscall (grith.ai)
		4 points by edf13 50 days ago \| past
11.		Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai)
		2 points by edf13 87 days ago \| past
12.		Mythos Proves AI Safety Can No Longer Live Inside the Model (grith.ai)
		3 points by edf13 89 days ago \| past
13.		The Risk Isn't Rogue AI. It's Plausible AI (grith.ai)
		2 points by edf13 3 months ago \| past
14.		AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai)
		3 points by edf13 3 months ago \| past \| 2 comments
15.		AI Makes Adding Features Faster – So Why Not Add Just One More? (grith.ai)
		2 points by edf13 3 months ago \| past
16.		Vibe Coding Still Needs a Senior Engineer (For Now) (grith.ai)
		5 points by edf13 4 months ago \| past \| 1 comment
17.		Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It (grith.ai)
		3 points by edf13 4 months ago \| past \| 1 comment
18.		The Vercel Breach Needed Malware. The Next One Needs a Bad Readme (grith.ai)
		1 point by edf13 4 months ago \| past \| 3 comments
19.		Every Claude 4.7 Improvement Makes the Security Problem Worse (grith.ai)
		5 points by edf13 4 months ago \| past \| 1 comment
20.		They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
		4 points by edf13 4 months ago \| past
21.		They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
		3 points by edf13 4 months ago \| past
22.		Prompt Injection Is Unfixable (So We Stopped Trying) (grith.ai)
		4 points by edf13 4 months ago \| past \| 1 comment
23.		If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised (grith.ai)
		5 points by edf13 5 months ago \| past
24.		Zero Ambient Authority: The Principle That Should Govern Every AI Agent (grith.ai)
		3 points by edf13 5 months ago \| past
25.		Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels (grith.ai)
		3 points by edf13 5 months ago \| past
26.		Claude now decides what's safe to run – a UX improvement, not a security fix (twitter.com/grithai)
		3 points by edf13 5 months ago \| past
27.		AI agents are now deciding what's safe to run (Claude Auto Mode) (grith.ai)
		3 points by edf13 5 months ago \| past
28.		The Trivy Supply Chain Attack Reached LiteLLM (grith.ai)
		3 points by edf13 5 months ago \| past \| 1 comment
29.		Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
		1 point by edf13 5 months ago \| past
30.		Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
		3 points by edf13 5 months ago \| past
		More