pii-redactorRedact sensitive information from text using a locally-hosted, zero-shot PII/PHI detection model.
Install via ClawdBot CLI:
clawdbot install m-newhauser/pii-redactorInstall clawguard-pii (uv):
Install clawguard-pii (uv)Requires:
Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://pypi.org/project/clawguard-pii/Audited Apr 18, 2026 · audit v1.0
Generated Oct 6, 2026
A company deploys an AI support agent that drafts responses containing customer data such as emails, phone numbers, and order details. Before each response is sent, the PII Redactor service scans the draft locally, and redacts detected entities. This prevents accidental leakage of sensitive customer information over chat channels.
A telehealth platform uses an LLM to summarize patient-doctor conversations into clinical notes. The PII Redactor intercepts the generated summary, redacting medical record numbers, patient names, and other PHI before storing or forwarding it to electronic health record systems. This maintains HIPAA compliance while benefiting from AI-assisted documentation.
A bank's internal AI assistant helps relationship managers draft client communications that often include account numbers, SSNs, or transaction details. The PII Redactor runs locally to strip these before the draft is sent, reducing regulatory risk and preventing accidental exfiltration of non-public personal information.
An HR AI agent generates welcome emails, policy summaries, and task lists that reference new hires' personal information like home addresses, phone numbers, and government IDs. The PII Redactor removes this data from all outbound responses, ensuring compliance with privacy regulations such as GDPR and CCPA.
A DevOps team uses an AI code review bot that analyzes pull requests and suggests improvements. The bot may inadvertently echo hardcoded API keys, tokens, or database connection strings. The PII Redactor, with its zero-shot detection covering API keys, redacts these secrets from the suggestions before they are displayed to developers.
The core PII Redactor is released under MIT-0, allowing free self-hosting. The business model monetizes through paid enterprise support, compliance audits, and managed deployment services. Revenue comes from annual support contracts and consulting fees.
A hosted version of the redaction service is offered with a free tier for limited usage, while advanced features like custom entity models, audit logs, and high-availability clustering require a paid subscription. For sensitive industries, an on-premise license is available at a premium. Revenue is generated from subscription tiers and one-time license fees.
The redaction capability is packaged as an API that other AI agent platforms can embed. Pricing is based on volume of characters processed or number of redaction calls. This model targets platform providers who want to offer built-in PII protection to their users.
💬 Integration Tip
Ensure the agent runtime can reach the local ClawGuard service (localhost or internal host) and set the CLAWGUARD_URL and CLAWGUARD_TOKEN environment variables. Always validate the URL to prevent exfiltration, and implement the fallback manual review process if the service is unreachable.
Scored Oct 6, 2026
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Senior SecOps engineer skill for application security, vulnerability management, compliance verification, and secure development practices. Runs SAST/DAST sc...