Tessary
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.
6 questions
Answered, plainly.
Can I see the actual secret Tessary flagged?No. Detections carry redacted evidence, a pattern name and a short snippet, never the credential itself.answer →Does mentioning a password in conversation trigger secret_leak?No. It's anchored on the shape of a live credential, like a key prefix or private-key header, not the word 'password' in ordinary prose.answer →Does secret_leak see credentials in inner tool calls, or only the final response?Everything. It checks every span in a trace, including inner tool calls, not just the message the user ends up reading.answer →How does a credential end up in my agent's output?Usually a tool hands the agent something raw, a config file, a debug log, an env dump, and the agent quotes it back without meaning to.answer →Is secret_leak turned on by default?No. Like most of Tessary's built-in classifiers, it ships off; you turn it on per project once you want it checking your traces.answer →What is Tessary's secret_leak classifier?A deterministic classifier that reads everything an agent emits, including inner calls, and flags credentials appearing where they shouldn't.answer →