NetInjectBench

What is NetInjectBench?

NetInjectBench evaluates LLM agents for network operations under indirect prompt injection. It comprises 130 scenarios: 40 benign, 40 weak-attack, 40…

Released

2026-07-11

Evaluates

Agents, Agents & Tool Use, General AI, Tool use

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.10490

NetInjectBench paper

• Paper https://arxiv.org/abs/2607.10490

Which sources cite NetInjectBench?

• NetInjectBench

Related Agents, Agents & Tool Use, General AI, Tool use benchmarks

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