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.
| Stars | 24 |
| Forks | 10 |
| Language | TypeScript |
| Category | AI 工具 |
| License | Apache-2.0 |
| Quality Score | 47.35/100 |
| Open Issues | 8 |
| Last Updated | 2026-06-03 |
| Created | 2026-02-15 |
| Platforms | node |
| Est. Tokens | ~65k |
Explore other popular ai 工具 tools:
agentshield-benchmark is Open benchmark for AI agent security tools — prompt injection, data exfiltration, tool abuse, provenance. It is categorized as a AI 工具 with 24 GitHub stars.
agentshield-benchmark is primarily written in TypeScript. It covers topics such as agent-security, ai-security, 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.
agentshield-benchmark is released under the Apache-2.0 license, making it free to use and modify according to the license terms.