More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    US & UK PII Guardrail — HIPAA, GLBA & UK GDPR Memory Filter

    1

    Client-side RAM filter validating and redacting US & UK identifiers (SSN, ITIN, ABA Routing, NHS, NINO) before LLM API calls.

    $39

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    US & UK PII Guardrail — HIPAA, GLBA & UK GDPR Memory Filter

    US & UK PII Guardrail — HIPAA, GLBA & UK GDPR Memory Filter

    Example session with this skill installed

    Sanitize this customer escalation log containing US executive data (SSN, NANP phone, Visa) and UK clinical consultation notes (NHS number, NINO, London postcode) before sending it to an LLM agent for diagnosis.

    • Read your context and instructions
    • Compiled the us & uk

    US & UK PII Guardrail: Redaction Audit Report

    • Input Text Characters: 8,920
    • Execution Environment: 100% Local RAM (Zero cloud telemetry)
    • Regulatory Framework: 🟢 HIPAA Safe Harbor & UK GDPR PASSED
    Detected EntityRaw Sensitive ValueRedacted Safe TokenChecksum / Validation
    US SSN219-45-7890<PII_US_SSN_01>✅ Area/Group Validated
    US Phone+1 415-555-2671<PII_US_PHONE_01>✅ NANP Compliant
    UK NHS Number943 476 5919<PII_UK_NHS_01>✅ Mod-11 Validated
    UK NINOQQ 12 34 56 A<PII_UK_NINO_01>✅ HMRC Format Match
    UK PostcodeSW1A 1AA<PII_UK_POSTCODE_01>✅ BS 7666 Match
    Credit Card4532-0151-1284-3328<PII_CREDIT_CARD_01>✅ Luhn Mod-10 Valid
    Anthropic Keysk-ant-api03-...<PII_API_KEY_01>✅ Credential Redacted

    Safe Payload Dispatched:

    All statutory US and UK identifiers sanitized. Zero risk of regulatory non-compliance or data leak.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    US & UK PII Masking Guardrail — Enterprise Memory Safe Harbor

    Client-side memory firewall validating and sanitizing statutory US and UK personal identifiers, HIPAA medical data, GLBA banking coordinates, and cloud credentials before LLM ingress.

    ⚡ Key Features & Engineering Guardrails:

    • Dual Jurisdictions Covered:
      • USA: SSN (strict Area/Group/Serial checks), ITIN (IRS range checks), ABA Routing Transit Numbers (Federal Reserve Mod-10), NANP Phone numbers, ZIP+4 codes, HIPAA medical records (Medicare MBI, ICD-10 conditions).
      • UK: NHS Numbers (10-digit Mod-11 weighted checksums), National Insurance Numbers (NINO HMRC rules), UK Bank Sort Codes (XX-XX-XX), Royal Mail Postcodes (BS 7666), UK Driving Licences.
      • Global: Credit/Debit Cards (Luhn Mod-10 for Visa, Mastercard, Amex, Discover), Cloud API Keys (OpenAI, Anthropic, AWS, GitHub, Stripe), RFC-compliant Emails, IPv4 addresses.
    • 100% Local-First RAM Execution: Zero cloud telemetry, zero external network requests.
    • Bidirectional Token Handover: Generates sequential tokens (<PII_US_SSN_01>, <PII_UK_NHS_01>) with deterministic local unmasking.
    • Developer Ready: Drop-in compatibility for Claude Code, Cursor, Windsurf, Codex CLI, and Git pre-commit hooks.

    📦 What's Included in the ZIP:

    • Production CLI & core sanitization engine (scripts/us_uk_pii_guardrail.py)
    • Full regulatory reference protocol (references/us_uk_pii_privacy_protocol.md)
    • Complete integration & unit test suite with 100% pass rate (scripts/test_us_uk_pii_guardrail.py)
    • Antigravity & Agent skill specification (SKILL.md)

    Focuses exclusively on US and UK identifiers. Requires local Python 3. Does not support real-time streaming audio or binary image files.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill prevents sensitive data leaks by redacting US and UK identifiers (like SSNs and NHS numbers) locally in RAM using mathematical checksums rather than just simple pattern matching, ensuring compliance with HIPAA and GDPR.

    It is a standalone Python 3 engine that can be integrated into any AI agent workflow via terminal commands or by importing the sanitization logic into your existing pipeline scripts.

    The skill performs all redaction in system memory without writing artifacts to disk, ensuring that raw sensitive data never leaves your secure local environment or reaches the cloud LLM.

    You will receive the core Python PII engine, a command-line interface for batch processing, and a validation test suite to verify the guardrail's integrity before deployment.

    Yes, the skill supports a `--json` flag that generates structured, sanitized payloads, making it easy to feed cleaned data directly into automated downstream API pipelines.

    Currently, the tool is optimized specifically for US and UK identifiers; support for additional regions or new identifier types would require a version update or custom configuration.

    New in LLM Ops