Cross-domain: sensitive-data leak guard on LLM prompts
Judges: one prompt about to be sent to an external LLM. Questions: noul:contains_client_confidential - ...; noul:contains_regulated_personal_data - .... Action: Block or redact.
STop tier. Meets A, and the payoff is major with high confidence.5.64
Key facts
- Vertical
- Cross-industry
- Function
- Agents & dev
- Status
- Idea
- Volume
- high
- Value
- major
- Risk
- high
- Evidence
- —
- Flags
- human-review
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "yes_no",
"question": "Does this input match the decision in “Cross-domain: sensitive-data leak guard on LLM prompts”?",
"input": "<input to classify>",
"output": "yes | no"
}Related use cases
Cite this
Copy a link in your preferred format.