Red-Team AI White-box red teaming for agentic AI apps. Reads your code, finds bugs specific to your stack — not generic prompt injections. Most LLM red-teaming tools are black-box: they treat your agent as an opaque endpoint and fire generic adversarial prompts at it. That finds the obvious stuff. It does not find the bug where your JWT secret is hardcoded in , or the path through tools that no single-call check would catch. Red-Team AI is built for that gap.
| Stars | 19 |
| Forks | 10 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 38.45/100 |
| Open Issues | 28 |
| Last Updated | 2026-05-26 |
| Created | 2026-03-06 |
| Platforms | python |
| Est. Tokens | ~1257k |
Explore other popular ai 工具 tools:
wb-red-team is Whitebox & Blackbox 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 . It is categorized as a AI 工具 with 19 GitHub stars.
wb-red-team is primarily written in Python. It covers topics such as agent-security-tools, agentic-ai, ai-agents.
You can find installation instructions and usage details in the wb-red-team GitHub repository at github.com/sundi133/wb-red-team. The project has 19 stars and 10 forks, indicating an active community.
wb-red-team is released under the MIT license, making it free to use and modify according to the license terms.