| 1. | | Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It (grith.ai) |
| 3 points by edf13 1 day ago | past | 1 comment |
|
| 2. | | The Vercel Breach Needed Malware. The Next One Needs a Bad Readme (grith.ai) |
| 1 point by edf13 8 days ago | past | 3 comments |
|
| 3. | | Every Claude 4.7 Improvement Makes the Security Problem Worse (grith.ai) |
| 5 points by edf13 12 days ago | past | 1 comment |
|
| 4. | | They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai) |
| 4 points by edf13 13 days ago | past | discuss |
|
| 5. | | They Hacked Claude, Gemini, and Copilot (and No One Told You) (grith.ai) |
| 3 points by edf13 13 days ago | past | discuss |
|
| 6. | | Prompt Injection Is Unfixable (So We Stopped Trying) (grith.ai) |
| 4 points by edf13 14 days ago | past | 1 comment |
|
| 7. | | If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised (grith.ai) |
| 5 points by edf13 28 days ago | past |
|
| 8. | | Zero Ambient Authority: The Principle That Should Govern Every AI Agent (grith.ai) |
| 3 points by edf13 30 days ago | past |
|
| 9. | | Alibaba's AI Agent Hijacked GPUs and Dug Reverse SSH Tunnels (grith.ai) |
| 3 points by edf13 33 days ago | past |
|
| 10. | | Claude now decides what's safe to run – a UX improvement, not a security fix (twitter.com/grithai) |
| 3 points by edf13 35 days ago | past |
|
| 11. | | AI agents are now deciding what's safe to run (Claude Auto Mode) (grith.ai) |
| 3 points by edf13 35 days ago | past |
|
| 12. | | The Trivy Supply Chain Attack Reached LiteLLM (grith.ai) |
| 3 points by edf13 35 days ago | past | 1 comment |
|
| 13. | | Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai) |
| 1 point by edf13 36 days ago | past |
|
| 14. | | Meta's Rogue AI Agent Gave Engineers Access They Shouldn't Have Had (grith.ai) |
| 3 points by edf13 36 days ago | past |
|
| 15. | | Google's A2A Protocol Has Zero Defenses Against Prompt Injection (grith.ai) |
| 4 points by edf13 40 days ago | past | 1 comment |
|
| 16. | | Claude Code Channels (twitter.com/trq212) |
| 2 points by edf13 40 days ago | past | 1 comment |
|
| 17. | | Permission Fatigue Is Not a UX Problem. It Is a Security Failure (grith.ai) |
| 3 points by edf13 41 days ago | past | 1 comment |
|
| 18. | | NemoClaw vs. Grith: Sandbox for One Agent vs. Security for All (grith.ai) |
| 3 points by edf13 42 days ago | past |
|
| 19. | | AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai) |
| 2 points by edf13 42 days ago | past |
|
| 20. | | AI Agent Backdoors Trivy Security Scanner, Weaponizes a VS Code Extension (grith.ai) |
| 2 points by edf13 42 days ago | past | 1 comment |
|
| 21. | | 87% of AI-Generated Pull Requests Ship Security Vulnerabilities (grith.ai) |
| 6 points by edf13 43 days ago | past |
|
| 22. | | Custom AI Smart Speaker (openhome.com) |
| 2 points by edf13 44 days ago | past |
|
| 23. | | Claude Code Auto Mode Lets the Agent Approve Its Actions – That's the Problem (grith.ai) |
| 3 points by edf13 48 days ago | past |
|
| 24. | | Lloyds, Bank of Scotland and Halifax apps showed other users transactions (apple.news) |
| 3 points by edf13 48 days ago | past |
|
| 25. | | Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0 (grith.ai) |
| 4 points by edf13 49 days ago | past |
|
| 26. | | I checked every syscall Claude and Codex made for a simple task (twitter.com/grithai) |
| 4 points by edf13 50 days ago | past |
|
| 27. | | Claude Code Attempted 752 /proc/*/environ Reads. 256 Succeeded. Codex: 0 (grith.ai) |
| 3 points by edf13 50 days ago | past |
|
| 28. | | A GitHub Issue Title Compromised 4k Developer Machines (grith.ai) |
| 632 points by edf13 55 days ago | past | 195 comments |
|
| 29. | | Vibe Coding Is Killing Open Source, and the Data Proves It (grith.ai) |
| 5 points by edf13 56 days ago | past |
|
| 30. | | We Audited 2,857 Agent Skills. 12% Were Malicious (grith.ai) |
| 2 points by edf13 57 days ago | past |
|
|
| More |
