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

Excerpt

arXiv:2608.30207v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) are agents powered by vision-language models (VLMs) that perceive a screen and operate an operating system through mouse, keyboard, and terminal interactions to automate everyday digital tasks. Their exposure to untrusted content creates a risk of indirect prompt injection (IPI), where an adversary embeds instructions in content the agent reads to redirect it toward actions that violate the user's intent. Evalua