Metraipolis › archive › dc_9ab6bad515ea

Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback — arXiv:2608.29381

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29381
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:43.307Z
SHA-256 of the archived text
32d8e678e23e9527344c5492553301595d6c35ceefce406c934d35ba74b4f776
Stable URL of this page
https://metraipolis.com/documento/dc_9ab6bad515ea

How to cite

Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback — arXiv:2608.29381 — arXiv (en), https://arxiv.org/abs/2608.29381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ab6bad515ea (Metraipolis archive dc_9ab6bad515ea, sha256 32d8e678e23e9527344c5492553301595d6c35ceefce406c934d35ba74b4f776)
BibTeX
@misc{dc9ab6bad515ea,
  title = {Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback — arXiv:2608.29381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ab6bad515ea; sha256 32d8e678e23e9527344c5492553301595d6c35ceefce406c934d35ba74b4f776},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are costly to reconstruct after failures. Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored. Correct rollback does not imply secure recovery: a faithfully restored checkpoint may resume an execution whose states, assumptions, and external effects never coexisted in any valid history. In this paper, we present the first systematic security study of checkpoint and rollback in existing agent systems. By examining representative agent C/R systems, we characterize the design space of existing C/R mechanisms and develop a general execution model that captures their recovery boundaries and state dependencies. From this model, we identify five fundamental failure modes spanning incomplete or inconsistent internal state, stale external dependencies, nondeterministic replay, and unrecorded external effects. We further demonstrate their security impact through three end-to-end attacks on Hermes, Cline, and LangGraph, enabling malware-verification bypass, unauthorized mail forwarding, and double payment. To systematically study these failures in practice, we develop a multi-agent analysis pipeline that reconstructs execution semantics, identifies violations of the five failure conditions, and validates them through actual rollback. Across five representative frameworks, our evaluation shows that these failures recur across heterogeneous C/R designs and stem from a common gap between the state restored by a checkpoint and the dependencies required for secure continuation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.29381 — 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 2026-10-17T07:28:26.754Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).