Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    hipaa readiness audit

    1

    Audits codebases for HIPAA Security Rule gaps, identifies PHI leaks, and maps BAA requirements.

    $16

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    hipaa readiness audit

    hipaa readiness audit

    Example session with this skill installed

    Audit our Node.js patient portal repo. We use OpenAI for summaries and Sentry for logging. Are we HIPAA ready?

    • Read your context and instructions
    • Compiled the hipaa readiness audit

    Findings

    1. §164.312(b): Audit Gap. Sentry logs capture request bodies containing PHI. No evidence of read-access logging.
    2. §164.308(b)(1): BAA Risk. OpenAI flow lacks an executed BAA; data contains 3 of 18 HIPAA identifiers.
    3. §164.312(a): Addressable. Missing documentation for encryption-at-rest.

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

    About this skill

    The problem

    Developers often assume their stack is HIPAA compliant because they use AWS or Bitlocker. They lack a concrete map of how their specific code violates the HIPAA Security Rule or which vendors require a BAA.

    What it does

    • Scans codebases for ePHI-handling defects and maps them to specific HIPAA Security Rule citations.
    • Identifies third-party vendors and AI providers that require a Business Associate Agreement (BAA).
    • Finds missing audit controls, including failures to log record access (reads) rather than just writes.
    • Detects ePHI leakage into client-side analytics, session replays, and unscrubbed error trackers.
    • Generates severity-rated findings structured for OCR investigators or hospital security reviews.

    Why this beats prompting it yourself

    Generic LLM prompts often confuse proposed 2025 rules with current law or treat addressable requirements as optional. This skill uses a strict reference snapshot to ensure citations are accurate and distinguishes between code-level safeguards and organizational policies.

    Use cases

    • Preparing for a hospital CISO security review or vendor questionnaire.
    • Auditing a healthtech repo to identify PHI exposure before a production launch.
    • Generating evidence to feed an official 164.308(a)(1) risk analysis.
    • Mapping AI usage to identify which LLM flows must stop due to missing BAAs.

    Known limitations

    Cannot verify physical safeguards (facility access) or administrative policies (employee training). Findings are unverified if repo access is not provided.

    Cannot scan physical facilities or verify internal policies. Reporting is limited to technical safeguards. Code scans alone never prove compliance.

    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 4 months ago

    Permissions

    No special permissions declared or detected

    Listed4 months ago

    What's inside

    Frequently Asked Questions

    The skill requires read-access to your codebase to scan for ePHI-handling logic, infrastructure-as-code configurations, and third-party integrations; it produces a severity-rated report mapped to specific HIPAA citations.

    General LLMs default to stale training data and describe the Security Rule's 2025 NPRM proposals (mandatory encryption, mandatory MFA) as if already in force — they aren't. OCR still enforces the current rule, and the NPRM's own target for final action is July 2027. This skill's reference snapshot is dated (last verified 2026-07-17) specifically to keep that distinction current, and every citation traces to that snapshot or is flagged CITATION TO VERIFY rather than asserted from memory.

    It fully covers Technical Safeguards (§164.312) via code scanning, and does substantial Administrative Safeguards work too — BAA mapping for every vendor touching ePHI (§164.308(b)(1)) and structuring findings to feed the §164.308(a)(1) risk analysis, the most-cited deficiency in OCR investigations. What it doesn't reach: Physical Safeguards (§164.310) and non-technical Administrative items like training programs and written policies — those need a human, not a code scan, and the skill flags them explicitly rather than silently skipping them.

    Yes, it specifically identifies API calls to AI providers and external telemetry tools to flag where a Business Associate Agreement (BAA) is legally required but missing.

    This skill is compatible with popular AI development agents and can be integrated into your existing CI/CD pipeline or run as a standalone audit on local and remote repositories.

    New in Agents & Orchestration