Metraipolis › archive › dc_08620ced1aca
Workspace Topology as an Attack Vector in Agentic Coding Assistants — arXiv:2608.14876
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14876
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:56:08.172Z
- SHA-256 of the archived text
ec820426602cce456e991faf6237189836f35553b6837ea0eee72d9ba2be9b1b- Stable URL of this page
https://metraipolis.com/documento/dc_08620ced1aca
How to cite
Workspace Topology as an Attack Vector in Agentic Coding Assistants — arXiv:2608.14876 — arXiv (en), https://arxiv.org/abs/2608.14876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08620ced1aca (Metraipolis archive dc_08620ced1aca, sha256 ec820426602cce456e991faf6237189836f35553b6837ea0eee72d9ba2be9b1b)
BibTeX
@misc{dc08620ced1aca,
title = {Workspace Topology as an Attack Vector in Agentic Coding Assistants — arXiv:2608.14876},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14876},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08620ced1aca; sha256 ec820426602cce456e991faf6237189836f35553b6837ea0eee72d9ba2be9b1b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious code being ingested as these coding tools operate with broad filesystem access inside developer workspaces. In this paper, we extensively study the impact of different dimensions of a novel attack surface we term workspace topology -- defined via directory depth, codebase modularity, in-file injection position and context framing -- on the attack success rate of adversarial prompt injection attempts. We perform an empirical study of indirect prompt injection (IPI) across a diverse set of open-source repositories spanning 10 languages and 6 engineering domains, evaluating three IPI entry points against open-weight models operating open source code harnesses. We find that workspace topology measurably affects IPI success. Specifically, changes in codebase modularity can significantly alter the Attack Success Rate (ASR), with highly modular environments demonstrating significantly lower attack success rates. Furthermore, context framing and introduction of security-cues in the workspace can also alter the ASR. Our findings offer practical value for the evaluation and security testing of coding agents across diverse settings, while underscoring the importance of an uncontaminated testing environment to obtain reliable results and conclusions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.14876 — 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 2026-10-18T16:29:13.963Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).