Sensitive data in prompts
In shortAn on-device check that catches personal data, card numbers or secret keys in a prompt before it reaches an AI provider.
Where it sits in EndLayer · step 6 of 7, decision
What it means
Built-in detectors look for one kind of sensitive data each. Depending on your policy, a match is recorded, warned on, redacted or blocked by a guardrail, and the matched text never leaves the machine.
Why it matters
It keeps customer data and secrets out of AI services without banning AI.