Xkcd

AI meets little bobby tables

The attack technique developed by Pillar Researchers, which they call ‘Rules File Backdoor,’ weaponizes rules files by injecting them with instructions that are invisible to a human user but readable by the AI agent.

xkcd taught me anything, its to sanitize my inputs


Quote Citation: Laura French, “How AI coding assistants could be compromised via rules file”, March 18, 2025, https://www.scworld.com/news/how-ai-coding-assistants-could-be-compromised-via-rules-file