edf13's submissions | Hacker News

1.		The Vercel Breach Needed Malware. The Next One Needs a Bad Readme (grith.ai)
		1 point by edf13 6 hours ago \| past \| 3 comments
2.		Every Claude 4.7 Improvement Makes the Security Problem Worse (grith.ai)
		5 points by edf13 4 days ago \| past \| 1 comment
3.		They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
		4 points by edf13 4 days ago \| past \| discuss
4.		They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai)
		3 points by edf13 5 days ago \| past \| discuss
5.		Prompt Injection Is Unfixable (So We Stopped Trying) (grith.ai)
		4 points by edf13 6 days ago \| past \| 1 comment
6.		If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised (grith.ai)
		5 points by edf13 20 days ago \| past
7.		Zero Ambient Authority: The Principle That Should Govern Every AI Agent (grith.ai)
		3 points by edf13 21 days ago \| past
8.		Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels (grith.ai)
		3 points by edf13 24 days ago \| past
9.		Claude now decides what's safe to run – a UX improvement, not a security fix (twitter.com/grithai)
		3 points by edf13 26 days ago \| past
10.		AI agents are now deciding what's safe to run (Claude Auto Mode) (grith.ai)
		3 points by edf13 26 days ago \| past
11.		The Trivy Supply Chain Attack Reached LiteLLM (grith.ai)
		3 points by edf13 27 days ago \| past \| 1 comment
12.		Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
		1 point by edf13 27 days ago \| past
13.		Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai)
		3 points by edf13 27 days ago \| past
14.		Google's A2A Protocol Has Zero Defenses Against Prompt Injection (grith.ai)
		4 points by edf13 31 days ago \| past \| 1 comment
15.		Claude Code Channels (twitter.com/trq212)
		2 points by edf13 32 days ago \| past \| 1 comment
16.		Permission Fatigue Is Not a UX Problem. It Is a Security Failure (grith.ai)
		3 points by edf13 32 days ago \| past \| 1 comment
17.		NemoClaw vs. Grith: Sandbox for One Agent vs. Security for All (grith.ai)
		3 points by edf13 33 days ago \| past
18.		AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai)
		2 points by edf13 33 days ago \| past
19.		AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai)
		2 points by edf13 33 days ago \| past \| 1 comment
20.		87% of AI-Generated Pull Requests Ship Security Vulnerabilities (grith.ai)
		6 points by edf13 35 days ago \| past
21.		Custom AI Smart Speaker (openhome.com)
		2 points by edf13 36 days ago \| past
22.		Claude Code Auto Mode Lets the Agent Approve Its Actions – That's the Problem (grith.ai)
		3 points by edf13 39 days ago \| past
23.		Lloyds, Bank of Scotland and Halifax apps showed other users transactions (apple.news)
		3 points by edf13 39 days ago \| past
24.		Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0 (grith.ai)
		4 points by edf13 40 days ago \| past
25.		I checked every syscall Claude and Codex made for a simple task (twitter.com/grithai)
		4 points by edf13 41 days ago \| past
26.		Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0 (grith.ai)
		3 points by edf13 41 days ago \| past
27.		A GitHub Issue Title Compromised 4k Developer Machines (grith.ai)
		632 points by edf13 46 days ago \| past \| 195 comments
28.		Vibe Coding Is Killing Open Source, and the Data Proves It (grith.ai)
		5 points by edf13 47 days ago \| past
29.		We Audited 2,857 Agent Skills. 12% Were Malicious (grith.ai)
		2 points by edf13 48 days ago \| past
30.		We Audited 2,857 Agent Skills. 12% Were Malicious (grith.ai)
		2 points by edf13 49 days ago \| past
		More

HN For You