Towards solution of this problem, I will create a “panel” in AIIM UI that will search using the AI API of user’s choice both prompt injections and hidden information.
A user after choosing the AI provider (such as OpenAI, Anthropic, or DeepSeek) and depth of the web search will be able by entering an URL or a reference to another user check the page(s) for prompt injections and hidden information.
Because prompt injections usually succeed not always and not for all models, there is expected a high probability that they will be found and the guilty person will be banned.
The AI API keys will be held in browser storage, never reaching our site.
Please donate toward me working on this defensive “panel”, because it needs to be done before the adversrial testing.
Help Turn AIIM’s Beta into Evidence
AIIM remains experimental. The next proposed milestone is a five-month public adversarial test, with $1,000 planned for distribution to eligible funding recipients. Donations support the work required to run and evaluate that test.
Fund the public test → Test proposal → Independent review →
AI-generated evaluations can contain factual errors or biases; decentralized governance and non-custodial components remain under development. Public testing, auditability, and external criticism remain part of the project.