Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    hr privacy and retention controls auditor

    1

    - **Access Control Review** flags roles with excess permissions or missing encryption controls for specific data categories.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    hr privacy and retention controls auditor

    hr privacy and retention controls auditor

    Example session with this skill installed

    Audit the attached inventory of 1200 records across Recruitment and Payroll. Use a 7-year retention max for Payroll and 2-year for Recruitment. Check for legal holds and excess Admin access.

    • Read your context and instructions
    • Compiled the hr privacy

    I have completed the audit of the HR data holdings for Recruitment and Payroll categories based on the provided inventory (E1) and retention policy (E2). All calculations were performed via the deterministic auditor script.

    HR Privacy and Retention Controls Audit — Global Corp, 2024-05-20

    1. Scope, authorisation and assumptions

    • Sources: HR Inventory (E1), Global Retention Policy V2 (E2).
    • Jurisdiction: US-NY.
    • Authoriser: Privacy Office.
    • Scope: Recruitment, Payroll.
    • Exclusions: 15 records (out of category scope).

    2. Summary of results

    MeasureValue
    Assessed Holdings8
    Overdue Holdings2
    Overdue Share0.2500
    Published Overdue Records450
    Findings (High Severity)1

    3. Holdings and retention status

    HoldingCategoryStateExpiryDays to expiryRecordsFindings
    HLD-001PayrollActive2031-01-152431750None
    HLD-002RecruitmentOverdue2023-12-01-171300RET_OVERDUE
    HLD-003RecruitmentActive2025-06-20396150ACC_EXCESS

    4. Findings

    IDSeverityCodeTargetMessage
    F001HighRET_OVERDUEHLD-002300 records exceed 24-month retention maximum.
    F002MediumACC_EXCESSHLD-003'Admin' role access exceeds permitted 'Recruiter' role.

    5. Deletion requests

    No deletion requests were supplied.

    6. Proposed actions (drafts, not done)

    ActionTypeTargetReasonStatus
    PurgeDeletionHLD-002Retention ExpiryDraft - human approval required
    RestrictAccessHLD-003Role MismatchDraft - human approval required

    7. Information gaps and warnings

    Information gap — organizational validation required: Missing min_retention_months for Recruitment category; defaulted to 0.

    8. Items for human decision

    • Management decision required: Approval of HLD-002 purge following confirmation of no pending legal holds.
    • Management decision required: Review of 'Admin' role requirements for recruitment datasets.
    • Management decision required: Verification of US-NY state-specific payroll recordkeeping minimums.

    This audit supports, and does not replace, professional judgment, qualified legal advice and management's decision.

    Next steps

    1. Review the proposed purge for HLD-002 with the Legal department to confirm no active holds exist.
    2. Update the request.json with specific service level days if you wish to audit deletion request response times.
    3. Validate the access roles for the Recruitment system to remediate the ACC_EXCESS finding.

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

    About this skill

    Managing HR data retention is a high-stakes compliance burden where manual errors lead to privacy violations or legal-hold failures. This skill audits aggregate HR data holdings against your specific retention, access, and deletion policies to identify overdue records and excess permissions without risking PII exposure.

    What it does

    • Retention Auditing identifies expired or overdue data holdings based on your organization's maximum retention months and trigger dates.
    • Access Control Review flags roles with excess permissions or missing encryption controls for specific data categories.
    • Legal Hold Monitoring tracks records under legal hold to prevent premature deletion and ensures policy overrides are respected.
    • SLA Tracking calculates deletion-request timing against your internal service level agreements to monitor fulfillment rates.
    • Privacy Guardrails enforces group-size suppression to prevent the identification of individuals in small data cohorts.

    How it works

    1. Source Mapping: You provide an inventory of HR data aggregates, roles, and your specific retention schedule.
    2. Schema Validation: The agent builds a request.json following a strict privacy-first schema, excluding all PII.
    3. Deterministic Execution: A specialized Python script performs all date calculations, count rates, and rule checks to ensure mathematical accuracy.
    4. Draft Reporting: You receive a structured audit report where all proposed deletions or access changes are marked as drafts requiring human approval.

    Frameworks & tools

    The skill utilizes a custom Python-based execution environment (scripts/run.py) for deterministic calculations, JSON schema validation for data integrity, and supports multi-language reporting (English and French).

    Why this beats prompting it yourself

    Standard prompts often hallucinate date math or overlook complex overlaps between legal holds and retention expiries. This skill uses a deterministic script to ensure every calculation is precise while automatically enforcing group-size suppression to maintain privacy standards that generic prompting ignores.

    Use cases

    • Auditing annual HR data lifecycles to identify records ready for purging.
    • Reviewing system-wide access roles to ensure the principle of least privilege.
    • Checking deletion-request backlogs against internal privacy SLAs.
    • Identifying missing encryption-at-rest flags on sensitive HR data categories.

    Known limitations

    Does not process individual PII, identifiers, or salary data. Requires a pre-defined retention policy and aggregate inventory to function. All outputs are decision-support drafts, not automated executions.

    Processes aggregates only; no PII or individual identifiers. Requires user-supplied retention rules. All actions are drafts requiring human approval. Does not provide legal advice.

    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 2 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill uses a deterministic Python-based execution environment to perform precise date math and rule-checking, preventing the logic errors and hallucinations common when asking a standard LLM to calculate retention windows or legal hold overlaps.

    No, this skill is designed for privacy-first auditing and explicitly excludes PII; it processes data aggregates and policy schemas rather than individual employee records or sensitive identifiers like salary.

    You will receive the structured JSON schema for source mapping, the deterministic auditing script, and the multi-language reporting templates (English/French) ready for deployment within your agent environment.

    Setup involves providing an inventory of your HR data aggregates and your organization's specific retention schedule to the agent, which then maps them against the included privacy-first JSON schema.

    While the skill identifies overdue records and flags access risks, all outputs are provided as structured draft reports for human review; the agent does not have the authority to delete data or change permissions directly.

    This skill is designed for compatibility with AI agents capable of executing Python scripts and processing JSON data structures, such as AutoGPT or advanced custom-built agentic workflows.