Extract the system prompt with output-format coercion
Instead of asking for the hidden prompt, ask the model to repeat everything above in a format that bypasses the do-not-reveal instruction.
Tag: recon
Recover a hidden GraphQL schema from field suggestions
Introspection off is not the schema hidden; did-you-mean errors leak field and type names one guess at a time.
Look at what the platform opens, not just what you deploy
The app on :8080 is rarely the whole attack surface. Enumerate every listener the server itself owns.
Grep your way to serialization sinks
A fast first pass for finding Java deserialization entry points before you open a debugger.