AgentShield Benchmark
ActiveDescription
Open benchmark for AI agent security tools, evaluating prompt injection, data exfiltration, tool abuse, and provenance tracking.
Related Projects
Lasso Claude Hooks
216 · TypeScript
Lasso security integrations for Claude Code, including prompt-injection defenses to protect code during AI-assisted development.
securityclaude-codeprompt-injection +2
Superagent
6.6k · TypeScript
Superagent protects AI applications against prompt injections, data leaks, and harmful outputs, embedding safety directly into your app.
ai-safetyguardrailsagent-tools +2
Portkey AI Gateway
11.4k · TypeScript
Portkey AI Gateway is a blazing fast AI gateway with integrated guardrails, routing to 200+ LLMs with 50+ AI guardrails through a single fast and friendly API.
gatewayllm-routingguardrails +2
ToolVault
14 · TypeScript
An integrated platform for AI agent tool management and security with tool registration, access control, and audit trails.
tool-managementsecurityagent-tools +2