sundi133/wb-red-team

White-box red-teaming framework for agentic AI apps. It analyzes your app's source code to discover tools, roles, and guardrails, then generates new attacks chains across several categories and adapts over multiple multi turn rounds to find vulnerabilities

39
/ 100
Emerging

Implements 85+ pluggable attack modules spanning authentication bypass, prompt injection, data exfiltration, and multi-turn escalation techniques, with a modular `AttackModule` interface enabling custom attack development. Uses LLM-powered adaptive attack chains that learn from previous rounds, targeting agentic systems built on common frameworks while analyzing source code to map tool definitions, role configurations, and guardrail implementations. Designed for integration into CI/CD pipelines and supports extensibility through community-contributed attack categories.

No Package No Dependents
Maintenance 13 / 25
Adoption 2 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

2

Forks

4

Language

TypeScript

License

MIT

Last pushed

Mar 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/sundi133/wb-red-team"

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