arXiv CSopen access
StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection
cryptography, security, privacy, cybersecurity
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Record · ID 440320
Retrieved via
Conceptio — every document is proof-bundled with source, license, and retrieval metadata.