StepJack Benchmark

What is StepJack?

StepJack evaluates computer-use agents against multi-step indirect prompt injection attacks, where adversarial goals are decomposed into innocuous sub-steps…

Released

2026-08-06

Evaluates

Agents, General AI, Safety, Safety & Trustworthiness

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.06477

StepJack paper and code

• Paper https://arxiv.org/abs/2608.06477
• Code https://github.com/BorealisAI/StepJack

Which sources cite StepJack?

• StepJack

Related Agents, General AI, Safety, Safety & Trustworthiness benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision