StepJack Benchmark
Explore score history ↗StepJack evaluates computer-use agents against multi-step indirect prompt injection attacks, where adversarial goals are decomposed into innocuous sub-steps across a chain of pages. It comprises 480 test examples across platforms and instruction types, with attack success rate as the primary metric.
- Released
- 2026-08-06
- Institutions
- Borealis (Austria)
- Evaluates
- Agents, General AI, Safety, Safety & Trustworthiness
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
StepJack paper and code
No reported scores are on record for this benchmark yet.