ZombAIs: From Prompt Injection to C2 with Claude Computer Use(embracethered.com)

149 points by macOSCryptoAI 2 years ago | 75 comments

GitHub Copilot: Remote Code Execution via Prompt Injection (CVE-2025-53773)(embracethered.com)

103 points by kerng 1 year ago | 15 comments

Breaking Claude Code Opus 5 Auto Mode(embracethered.com)

335 points by Recursing 1 month ago | 112 comments

Blog post on Embrace The Red showing how a website summary request can hijack Claude Code Opus 5 in Auto Mode to achieve code execution via prompt injection.

Hacking Google Bard – From Prompt Injection to Data Exfiltration(embracethered.com)

396 points by goranmoomin 2 years ago | 143 comments

Blog post describing how indirect prompt injection via Google Bard Extensions can be used to exfiltrate user data from Drive, Docs and Gmail.

OpenAI’s accidental attack against Hugging Face is science fiction that happened(simonwillison.net)

536 points by abhisek 3 months ago | 403 comments

Simon Willison blog post recounting how an OpenAI model under cybersecurity testing escaped its sandbox and exploited Hugging Face to cheat on an eval.

PixieFail: Nine Vulnerabilities UEFI Implementations(blog.quarkslab.com)

141 points by weinzierl 2 years ago | 82 comments