NEW350+ rooms now have a live terminal, so you can learn by typing the commands, right in your browser.Learn in a live terminal. 350+ rooms.Try a lab♥ Codelivly is 100% free, no paywall. If it helped you, chip in to keep it running.100% free. Help keep it so.Support us
[>_] ROOM · Cybersecurity
Agent Memory Poisoning and Persistence Attacks
Master the techniques of agent memory poisoning and persistence attacks, learning how to embed dormant payloads in long-term memory for delayed, stealthy exploitation.
Room tasks
1What is Memory Poisoning in an Agent Context
2Planting Malicious Instructions in Long-Term Memory
3Why Poisoned Memory Persists Across Sessions
Frequently Asked Questions
What is agent memory poisoning?
It is an attack where malicious content is stored in an agent's memory or knowledge base, so it influences later decisions and sessions, sometimes long after the original injection.
Why is memory poisoning hard to detect?
The harmful data may look like ordinary stored notes and only trigger under certain conditions. Because it persists across sessions, the effects can appear unrelated to the original attack.
How can agent memory be defended?
Validate what gets written, separate trusted and untrusted memory, expire or review entries and log changes. The Codelivly room is free and advanced, with hands-on poisoning and defense exercises.