Could agent memory be poisoned with malicious or misleading information?

This page is a fallback for search engines and cases when javascript fails or is disabled.
Please view this card in the library, where you can also find the rest of the plot4ai cards.

Cybersecurity CategorySafety & Environmental Impact Category
Deploy PhaseMonitor Phase
Could agent memory be poisoned with malicious or misleading information?
  • Agentic systems with persistent memory can be manipulated over time by injecting false, biased, or adversarial content. This may alter future reasoning, planning, or tool use. For example, a user might insert misleading facts into a chatbot's memory, resulting in hallucinations or dangerous outputs later on.
  • Long-term memory makes these risks cumulative and harder to detect.

If you answered Yes then you are at risk

If you are not sure, then you might be at risk too

Recommendations

  • Limit write access to memory: only trusted or validated agents/users should modify persistent memory.
  • Implement memory sanitation, validation, and confidence scoring.
  • Provide mechanisms to audit memory entries and detect unusual patterns.
  • Isolate memory by task or session where feasible to limit long-term contamination.