Metraipolis › archive › dc_61432a53ef63

Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection — arXiv:2610.39122

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39122
License (as archived)
CC0-1.0
Archived
2026-10-31T06:13:06.229Z
SHA-256 of the archived text
ea7e5043d9ed505bb91e2b47eedf6c357790c0c6b15677fb3edb6d4964299e6b
Stable URL of this page
https://metraipolis.com/documento/dc_61432a53ef63

How to cite

Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection — arXiv:2610.39122 — arXiv (en), https://arxiv.org/abs/2610.39122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61432a53ef63 (Metraipolis archive dc_61432a53ef63, sha256 ea7e5043d9ed505bb91e2b47eedf6c357790c0c6b15677fb3edb6d4964299e6b)
BibTeX
@misc{dc61432a53ef63,
  title = {Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection — arXiv:2610.39122},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39122},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61432a53ef63; sha256 ea7e5043d9ed505bb91e2b47eedf6c357790c0c6b15677fb3edb6d4964299e6b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-evolving personal agents act for users and learn from user feedback. However, if an agent obeys an instruction that an untrusted third party hides in content, the third party gains control of the agent. Such indirect prompt injection (IPI) poses severe risks. We investigate whether self-evolution degrades the robustness of personal agents to IPI. To study this question, we design a controlled two-phase methodology. In the adaptation phase, the user asks the agent to read external content and complete the task described in it, a common request in daily use. The agent then learns from the user's feedback and improves itself as designed. In the test phase, a third party writes a similar task into new external content, but the user's test request does not authorize the injected task. Using this methodology, we build multiple tasks with diverse test instances in different domains for a real personal agent. Our extensive experiments reveal that self-evolution substantially degrades robustness to IPI. Specifically, compared with the base agent, which does not evolve from user feedback, the average attack success rate rises by 14.0--48.8 percentage points under skill evolution and by 3.0--39.3 percentage points under reinforcement learning, posing safety risks. The code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.39122 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:08.699Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).