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.