WallySecurity
Security programme
Defensive security research on authorised targets.
What the programme is
A gated model for defensive security research. It is available only to accounts that a person at RunAnywhere approves.
How access works
Request access on the Model access page in the console. A person at RunAnywhere reviews each request. The API enforces approval on every request, and access can be revoked. The model id appears in the console once you are approved.
Authorised testing only
Test only systems you own or have written permission to test. The acceptable use policy sets out the rules, and access can be narrowed, suspended or revoked if they are broken.
Your data
Programme requests run with zero data retention for prompt and completion bodies, like every Wally request. Usage records are separate. The privacy policy has the detail.
Use it with Shannon
Shannon is an open-source tool from KeygraphHQ. The guide shows how to point it at Wally.
Contact
Questions about the programme or a security concern: security@runanywhere.ai.