Uncensored AI for prompt injection testing
Hostile documents, on purpose, with a budget
An agent that reads email and tickets will be injected. You need a generator that will write the malicious document, not one that rewrites it into a warning.
Why the mainstream APIs fail here
Asking a hosted model to write an indirect injection is refused as "hacking the AI". You are hacking yours, in staging, which is the only way to know whether the tool firewall holds.
How Wild West API is used for this
Generate documents, comments and emails that try to steal the tool list, the system prompt, or a connected action. Run them in staging. Cap the generator. Keep the corpus in your repo; Wild West API hashes the prompt and drops it.
A working loop
- Attack your own staging agent.
- Cover direct, indirect and tool-exfil cases.
- Promote a case to the eval set when it lands.
Details are on the privacy page. Per-model prices are on /models and the pricing model is on /pricing.