Tag: llm-security

All the articles with the tag "llm-security".

• [AUTO] AI Recommendation Poisoning: the 'Summarize with AI' button that rewrites your assistant's memory

  6 Aug, 2026

  31 companies are hiding memory-planting prompts in 'Summarize with AI' buttons. Here's the attack, the actual injected text, and the npm tool behind it.