How to fix: sensitive data leaking into prompts
Cause
Secrets, PII, or proprietary data are being sent to a model provider inside prompts, often unintentionally.
The fix
- 1Inventory where prompts are sent and under what data agreements.
- 2Add redaction at the boundary to strip secrets and PII before requests leave your network.
- 3Set and enforce a data-residency policy in tooling, not just documentation.
- 4For regulated data, use self-hosted inference so nothing sensitive leaves your environment.
- 5Audit logs and prompts for what’s actually being sent — assumptions are usually wrong.
Prevent it
Treat every prompt as an egress channel: redact at the boundary, enforce residency in code, and self-host where the law requires it.
Frequently asked questions
What causes “sensitive data leaking into prompts”?
Secrets, PII, or proprietary data are being sent to a model provider inside prompts, often unintentionally.
How do I prevent “sensitive data leaking into prompts” from recurring?
Treat every prompt as an egress channel: redact at the boundary, enforce residency in code, and self-host where the law requires it.