doronp/agentshield-benchmark

Open benchmark for AI agent security tools — prompt injection, data exfiltration, tool abuse, provenance

2 best points · 1 comments · 1 Hacker News post · 29 GitHub stars · View on GitHub

Hacker News discussions

• AGentShield – Open benchmark of 6 AI agent security tools (537 test cases) (2 points, 1 comments, by doronp, 2026-02-15)