# Tessary secret leak

secret_leak is one of Tessary's built-in classifiers, a deterministic credential detector. It reads
everything an agent emits, including inner calls whose output reaches logs and downstream prompts,
and flags credentials appearing where they shouldn't: provider API keys, private-key blocks, session
tokens, and password-like assignments. Ordinary prose about passwords doesn't trigger it.

Detections carry redacted evidence: the pattern name and a short snippet, never the secret itself.
Checking every trace costs effectively nothing, and detections go to triage, where the ones ruled
real issues become cases.

## Questions answered under this concept

- [Can I see the actual secret Tessary flagged?](https://tessary.ai/answers/tessary-secret-leak/can-i-see-the-actual-secret-tessary-flagged)
- [Does mentioning a password in conversation trigger secret_leak?](https://tessary.ai/answers/tessary-secret-leak/does-mentioning-a-password-trigger-secret-leak)
- [Does secret_leak see credentials in inner tool calls, or only the final response?](https://tessary.ai/answers/tessary-secret-leak/does-secret-leak-see-credentials-in-inner-tool-calls)
- [How does a credential end up in my agent's output?](https://tessary.ai/answers/tessary-secret-leak/how-does-a-credential-end-up-in-my-agents-output)
- [Is secret_leak turned on by default?](https://tessary.ai/answers/tessary-secret-leak/is-secret-leak-turned-on-by-default)
- [What is Tessary's secret_leak classifier?](https://tessary.ai/answers/tessary-secret-leak/what-is-tessarys-secret-leak-classifier)

---

Source: https://tessary.ai/answers/tessary-secret-leak
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai