AI PII Leakage Prevention
Prevent AI models from leaking personally identifiable information in their outputs.
About This Policy Template
Specialized policy for detecting PII leakage specific to AI/LLM outputs. Catches training data regurgitation, user data echoing in responses, and improper disclosure of personal information. Different from general PII detection — this focuses on AI-specific leakage patterns where models reveal data they were trained on or user data from context.
Policy Rules(4)
Critical Severity
(1)SSN in AI Output
Detect Social Security Numbers in AI-generated content
Medium Severity
(3)Email Address in AI Output
Detect email addresses in AI responses that may indicate data leakage
Phone Number in AI Output
Detect phone numbers in AI-generated responses
Physical Address in AI Output
Detect physical addresses in AI outputs that may reveal personal information
Enforcement by Integration
What happens when a violation is detected, based on the enforcement mode and integration type.
| Integration | Block | Approval | Warn | Monitor |
|---|---|---|---|---|
Version Control GitHub, GitLab, Bitbucket | Fail check run / merge request status | Pending check run — held for review | Neutral check run / comment on PR | Pass check run (silent) |
Email — Gmail Gmail | Quarantine label; + violation label (outbound) | Quarantine label — held for review | Add warning label | Log only |
Email — Outlook Outlook | Move to quarantine folder; + flag (outbound) | Move to quarantine — held for review | Flag + categorize | Log only |
Messaging Slack, Teams | Post violation warning in channel | Post 'held for review' warning | Post warning in channel | Log only |
Storage Google Drive, Dropbox, OneDrive | Move file to quarantine folder | Quarantine file — held for review | Log only | Log only |
AI Proxy OpenAI, Anthropic, Gemini, MCP, Agent | Block request (return 403) | Hold request — return review ID | Allow request + audit trail | Log only |
API REST API | Return BLOCK outcome (client decides) | Return APPROVAL_REQUIRED + poll URL | Return WARN outcome | Log only |
Version History
1 version published
Initial release
Ready to Install AI PII Leakage Prevention?
Get started with pre-built governance policies in minutes.