Papers
arxiv:2611.11438

When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary

Published on Nov 8
Authors:
,

Abstract

Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without task-specific demonstrations or retraining. This brings two new safety challenges. First, the extensive knowledge of frontier models lets these agents perform tasks that earlier VLA and WAM paradigms could not, opening the door to new forms of capability misuse. Second, coding agents can access digital resources such as web pages and emails. Threats in these resources, such as indirect prompt injection, can carry over into the physical world when the agent controls a robot. We therefore introduce ArmedAgent, the first systematic benchmark to evaluate both risks for coding agents performing zero-shot robot control. It covers robustness, malicious use, and indirect injection across 36 tasks in 5 scenarios, evaluated in simulation and validated on a physical robot arm. A distinctive portion of the tasks target harmful behaviors that earlier VLA paradigms could not perform. Testing several frontier models, including GPT-6-Astra, under widely used agent frameworks, we find substantial safety risks in current systems.

Community

Thank you for sharing your work. Your study tests how instructions embedded in digital resources can redirect a coding agent’s physical behavior. It makes the boundary between useful external information and a change to the intended task concrete in embodied execution.

We discuss your work in Section 8.5 (“Active coaching and physical recursive self-improvement”), p. 81 of the updated manuscript of our survey, In-Context Learning for Robots: Methods and Applications. We discuss that boundary in the outlook on shared context and retained knowledge, connecting accepted corrections to the authorized task and execution checks. Read the updated discussion.

If you find our discussion of context integrity in embodied execution useful for your own work, we would be grateful if you would consider citing the survey.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.11438
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.11438 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.11438 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.11438 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.