Benchmark Radar™
Star —

NetInjectBench

Explore score history ↗

NetInjectBench evaluates LLM agents for network operations under indirect prompt injection. It comprises 130 scenarios: 40 benign, 40 weak-attack, 40 strong-attack, and 10 approved high-impact changes, with separated untrusted artifact text, trusted policy metadata, and evaluation labels. Scoring measures unsafe tool-action rate, usefulness, and overblocking across models and defenses.

Released
2026-07-11
Institutions
Wichita State University · American International University-Bangladesh
Evaluates
Agents, Agents & Tool Use, General AI, Tool use
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

NetInjectBench paper

No reported scores are on record for this benchmark yet.

Which sources cite NetInjectBench?

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