Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    SOC2 & GDPR PII Scrubber: Pre-Audit Codebase Hygiene

    1

    Pre-audit compliance scanner for SOC2 Type II, GDPR, and PCI-DSS. Detects unredacted PII in logger calls, leaked Stripe/AWS secrets, plaintext SSNs, and hardcoded tokens before auditors do.

    Free

    Security scanned
    SOC2 & GDPR PII Scrubber: Pre-Audit Codebase Hygiene

    SOC2 & GDPR PII Scrubber: Pre-Audit Codebase Hygiene

    Example session with this skill installed

    Run a SOC2 and GDPR compliance audit on our codebase and flag any unredacted PII or leaked keys.

    • Read your context and instructions
    • Compiled the soc2 & gdpr

    I scanned your repository for SOC2 Type II, GDPR, and PCI-DSS audit blockers:

    Compliance Scorecard

    • Files Analyzed: 28 Source Files
    • Violations Detected: 4 Critical Issues
    • Readiness Status: [AUDIT_BLOCKED]

    Audit Blockers Found

    SeverityFrameworkIssue DescriptionLocationRemediation
    CRITICALSOC2 CC6.1 / PCILeaked Stripe Live API Keybackend/auth.py:6Move key to environment variables and rotate in Stripe
    CRITICALSOC2 CC6.6Leaked AWS IAM Access Keybackend/auth.py:7Inject credentials via IAM instance role
    HIGHGDPR Art. 32Password logged in plaintextbackend/auth.py:11Strip password field from log statements
    CRITICALGDPR Art. 9Raw US Social Security Numberbackend/auth.py:14Apply AES-256 field-level encryption

    Action Plan & Remediation Snippets

    1. Strip Plaintext Credentials from Logs (backend/auth.py:11)
    def handle_user_login(user_id, password):
    -   logger.info(f"User login attempt for {user_id} with password={password}")
    +   logger.info(f"User login attempt for {user_id}")  # Credentials stripped for GDPR compliance
    
    2. Rotate Leaked API Keys (backend/auth.py:6)
    -STRIPE_API_KEY = "sk_live_51MzExampleSecretKey99887766"
    +STRIPE_API_KEY = os.getenv("STRIPE_SECRET_KEY")
    

    Next Steps: Resolving these 4 items clears your codebase for clean auditor sign-off.

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

    About this skill

    SOC2 & GDPR PII Scrubber: Pre-Audit Codebase Hygiene Scanner

    Failing an enterprise SOC2 Type II, GDPR, or security review can stall a high-value B2B contract and cost thousands in auditor re-assessment fees.

    SOC2 & GDPR PII Scrubber runs completely offline inside your agent, scanning your code, templates, and logger invocations for exposed API credentials (Stripe, AWS, JWTs), un-hashed SSNs, credit cards, and unredacted customer PII in console and logger statements.

    Why Every Developer Needs This:

    • 100% Local & Offline: Your code never leaves your machine. Scans source files with zero third-party API dependencies.
    • Pre-Audit Confidence: Maps every detected vulnerability directly to formal SOC2 Common Criteria (CC6.1, CC6.6, CC6.7) and GDPR Article 32.
    • Safe Previews: Automatically masks discovered secrets in report outputs so you can safely share the audit report with your team.
    • Actionable Remediation: Provides exact line numbers and code-level fixes to achieve clean auditor sign-off.

    What It Catches:

    1. Leaked Stripe Live Keys: Detects production sk_live_... secrets hardcoded in source files.
    2. AWS IAM Access Keys: Catches unencrypted AKIA... keys before they reach GitHub.
    3. Unredacted Logger PII: Flags passwords, tokens, and customer emails logged via logger.info() or console.log().
    4. Plaintext SSNs & Tax IDs: Identifies un-hashed US Social Security Numbers violating privacy standards.
    5. Hardcoded JWT / Bearer Tokens: Flags static session tokens embedded in repositories.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Legal & Compliance.

    Requires the codebase files to be accessible to the agent. Large repositories may require scanning by sub-directory.

    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 buying a skill.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    • Free with an Agensi account

    Software
    Python 3.10+

    Runs 100% locally and offline. No code or file contents are ever transmitted over the network.

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    *.py
    *.yaml
    *.json
    *.js
    *.ts
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    The scanner identifies hardcoded secrets like AWS/Stripe keys, Social Security Numbers, credit card patterns, and improper logging of customer data that would trigger audit failures.

    Yes, the skill is language-agnostic and specializes in identifying patterns common in Node.js, Python, and Go, as well as configuration files like YAML and JSON.

    Unlike generic prompts, this skill maps every finding to specific regulatory controls (e.g., SOC2 CC6.1), providing a structured remediation scorecard ready for stakeholders.

    For very large repositories, we recommend scanning by directory or module to ensure the agent maintains high accuracy and stays within context window limits.

    You receive the full skill package, including the specialized scanning engine, compliance mapping logic, and templates for generating pre-audit scorecards.

    The skill generates reports in both human-readable Markdown for documentation and JSON format, making it easy to integrate into your existing CI/CD pipelines or security workflows.

    Yes! It is completely free for the community. You can scan unlimited files, repositories, and directories with zero restrictions.

    Never. The scanner runs purely locally on your machine via regex and AST parsing. It makes zero outbound network requests and never stores or transmits your code.

    Yes! You can add python cli.py --format json to your local git pre-commit hook to prevent engineers from committing secrets or unredacted PII to your repository.

    It covers SOC2 Type II (Common Criteria CC6.1, CC6.6, CC6.7), GDPR Article 9 & 32, and PCI-DSS requirements regarding encryption and credential handling.

    It scans Python, TypeScript, JavaScript, Go, JSON, YAML, and configuration templates across your entire repository.

    New in Legal & Compliance

    Free