toxy4ny/kevlar-benchmark

Kevlar Benchmark: OWASP Top 10 for Agentic Apps (AI-Agents) 2026 a Red Team Benchmark

38
/ 100
Emerging

Automated red-team framework that tests all 10 OWASP Agent-Specific Injection (ASI) vulnerabilities through modular exploit simulators (goal hijacking, RCE chains, memory poisoning) ordered by real-world attack criticality. Includes a prioritized threat orchestrator, detection engines for data exfiltration and goal drift, and AIVSS scoring integration. Supports both mock and real LangChain agent modes via CLI with individual ASI test scripts, CI/CD integration, and structured JSON reporting.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

27

Forks

4

Language

Python

License

MIT

Last pushed

Jan 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/toxy4ny/kevlar-benchmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.