English => News => Topic started by: Redaktion on May 13, 2025, 22:24:06
Title: Study shows memory attacks can hijack AI agents to transfer crypto assets
Post by: Redaktion on May 13, 2025, 22:24:06
Princeton researchers expose a "memory poisoning" flaw in LLM agents: malicious context injections buried in vector stores can override guardrails and hijack crypto wallets.