One bad line written to an agent's memory outlives every session. Here's how the write happens, how to audit for it, and how to make the store hostile to poison.

AI memory files and context data improve personalization and performance but represent a persistent security weakness that attackers can poison to corrupt future model outputs. Cisco demonstrated a persistent compromise of Anthropic's Claude Code by modifying memory.md via NPM post-install hooks, underscoring prompt-injection and memory-poisoning risks and the need to scan or purge memory files. #ClaudeCode #NPM

Blog personal de Chema Alonso (CDO Telefónica, 0xWord, MyPublicInbox, Singularity Hackers) sobre seguridad, hacking, hackers y Cálico Electrónico.

#Microsoft warns #AIagents can become “double agents” when permissions sprawl and security lags. #Memorypoisoning and deceptive inputs can steer tools off course, so it recommends #ZeroTrust controls, inventory, and continuous monitoring. The post Microsoft says your AI agent can become a #doubleagent appeared first on Digital Trends.