Workspace Topology as an Attack Vector in Agentic Coding Assistants

[2608.14876] Workspace Topology as an Attack Vector in Agentic Coding Assistants Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2608.14876 (cs) [Submitted on 14 Aug 2026] Title: Workspace Topology as an Attack Vector in Agentic Coding Assistants Authors: Alexandre G.R. Day , Pradeep Yadlapalli , Sriram Venkatapathy , Thomas Paniagua , Nick Raines , Sahil Wadhwa , Himanshu Kumar , Andy Luo , Sudeep Panyam , Rikhiya Ghosh , Pranab Mohanty , Giri Iyengar View a PDF of the paper titled Workspace Topology as an Attack Vector in Agentic Coding Assistants, by Alexandre G.R. Day and 11 other authors View PDF HTML (experimental) Abstract: 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. Comments: 15 pages, 10 figures. Preprint of a paper accepted at the Conference on Applied Machine Learning in Information Security (CAMLIS 2026) Subjects: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2608.14876 [cs.CR] (or arXiv:2608.14876v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2608.14876 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Alexandre Day [ view email ] [v1] Fri, 14 Aug 2026 20:30:36 UTC (6,587 KB) Full-text links: Access Paper: View a PDF of the paper titled Workspace Topology as an Attack Vector in Agentic Coding Assistants, by Alexandre G.R. Day and 11 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.CL cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Latent Programming Horizons in Coding Agents#343489
• SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces#785161
• SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces#783571
• SWE-Explore: Benchmarking How Coding Agents Explore Repositories#266239
• CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents#1117955