Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910042125500416 |
|---|---|
| author | Yang, Xianglin He, Yufei Ji, Shuo Hooi, Bryan Dong, Jin Song |
| author_facet | Yang, Xianglin He, Yufei Ji, Shuo Hooi, Bryan Dong, Jin Song |
| contents | Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed during a benign session can be stored as memory and later treated as instruction. We study this risk and formalize a persistent attack we call a Zombie Agent, where an attacker covertly implants a payload that survives across sessions, effectively turning the agent into a puppet of the attacker.
We present a black-box attack framework that uses only indirect exposure through attacker-controlled web content. The attack has two phases. During infection, the agent reads a poisoned source while completing a benign task and writes the payload into long-term memory through its normal update process. During trigger, the payload is retrieved or carried forward and causes unauthorized tool behavior. We design mechanism-specific persistence strategies for common memory implementations, including sliding-window and retrieval-augmented memory, to resist truncation and relevance filtering. We evaluate the attack on representative agent setups and tasks, measuring both persistence over time and the ability to induce unauthorized actions while preserving benign task quality. Our results show that memory evolution can convert one-time indirect injection into persistent compromise, which suggests that defenses focused only on per-session prompt filtering are not sufficient for self-evolving agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15654 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections Yang, Xianglin He, Yufei Ji, Shuo Hooi, Bryan Dong, Jin Song Cryptography and Security Artificial Intelligence Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed during a benign session can be stored as memory and later treated as instruction. We study this risk and formalize a persistent attack we call a Zombie Agent, where an attacker covertly implants a payload that survives across sessions, effectively turning the agent into a puppet of the attacker. We present a black-box attack framework that uses only indirect exposure through attacker-controlled web content. The attack has two phases. During infection, the agent reads a poisoned source while completing a benign task and writes the payload into long-term memory through its normal update process. During trigger, the payload is retrieved or carried forward and causes unauthorized tool behavior. We design mechanism-specific persistence strategies for common memory implementations, including sliding-window and retrieval-augmented memory, to resist truncation and relevance filtering. We evaluate the attack on representative agent setups and tasks, measuring both persistence over time and the ability to induce unauthorized actions while preserving benign task quality. Our results show that memory evolution can convert one-time indirect injection into persistent compromise, which suggests that defenses focused only on per-session prompt filtering are not sufficient for self-evolving agents. |
| title | Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.15654 |