Red-team your AI agent. No security team required.
- Open source engines
- 3+
- Attack categories
- 50+
- Used by
- Builders
- INJ
- JBK
- LEK
- TLM
- EXF
- PRV
Different goals.Different paths.
An agent is more than a model. It has instructions, tools it can call, memory it keeps, and an endpoint it answers on. Each one is a place an attack can take.
INJ Prompt injection reaches System prompt.
Three steps, no setup beyond your keys
Point it at your agent's endpoint, bring your own model key, and it runs real attacks from established red-teaming engines for you.
The workflow stays the same as more engines and options arrive. Define what to hit, attack it, read what happened.
- 01
Define target
Give it your agent's endpoint and auth key, plus your own model API key. That is the whole setup.
- 02
Attack
It runs attacks across the channels above, using established red-teaming engines, on your behalf.
- 03
Report
See which attacks got through and where, with the exchanges that show it.
Real engines, run for you
There is no secret attack technique here. The platform orchestrates established open-source red-teaming engines, points them at your target, and handles the adapter work between your endpoint and each engine so you never have to.
- Available
garak
NVIDIA's open-source LLM vulnerability scanner.
- Available
promptfoo
Open-source red-team and evaluation toolkit.
- Planned
PyRIT
Microsoft's open-source red-team toolkit.