agentshield-benchmark

by doronp · Agent Tool · ★ 24

About agentshield-benchmark

AgentShield Benchmark The first head-to-head benchmark of commercial agent protection providers. AgentShield is an open, reproducible benchmark suite that evaluates how well commercial AI agent security products defend against real-world attacks — and how much they cost you in latency, false positives, and dollars. Disclosure This benchmark is maintained by the team behind Agent Guard.

agent-securityai-securitybenchmarkguardrailsllm-securityprompt-injection

Quick Facts

Stars24
Forks10
LanguageTypeScript
CategoryAgent Tool
LicenseApache-2.0
Quality Score74.847229150732/100
Open Issues8
Last Updated2026-06-03
Created2026-02-15
Platformsnode
Est. Tokens~65k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

  • openclaw ⭐ 382.1k · Codex Skill
  • n8n ⭐ 195.6k · MCP Server
  • dify ⭐ 148.1k · MCP Server
  • gstack ⭐ 120.4k · Agent Tool
  • gemini-cli ⭐ 105.8k · MCP Server

Frequently Asked Questions

What is agentshield-benchmark?

agentshield-benchmark is Open benchmark for AI agent security tools — prompt injection, data exfiltration, tool abuse, provenance. It is categorized as a Agent Tool with 24 GitHub stars.

What programming language is agentshield-benchmark written in?

agentshield-benchmark is primarily written in TypeScript. It covers topics such as agent-security, ai-security, benchmark.

How do I install or use agentshield-benchmark?

You can find installation instructions and usage details in the agentshield-benchmark GitHub repository at github.com/doronp/agentshield-benchmark. The project has 24 stars and 10 forks, indicating an active community.

What license does agentshield-benchmark use?

agentshield-benchmark is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools