SOURCE-LINKED INTELLIGENCE

SIR: Self-improving Red-teaming for Compute Use Agents

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate everyday digital tasks. Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI), in which an adversary plants instructions in content the agent will read and redirects it toward actions that violate the user's intent. Existing CUA safety benchmarks evaluate fixed injections written by hand, which may underestimate the risk posed by an

Read original source ↗ Open in workspace

recordType

paper

region

Global