HIPAA Safe Harbor Coverage Audit
maziyarpanahi/openmed
Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.
Audit applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule…
$ npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install briiirussell/cybersecurity-skills hipaa-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/briiirussell/cybersecurity-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hipaa-audit .claude/skills/hipaa-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hipaa-audit" agent skill from https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-audit into .claude/skills/hipaa-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hipaa-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install briiirussell/cybersecurity-skills hipaa-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/briiirussell/cybersecurity-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hipaa-audit .agents/skills/hipaa-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hipaa-audit" agent skill from https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-audit into .agents/skills/hipaa-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hipaa-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install briiirussell/cybersecurity-skills hipaa-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/briiirussell/cybersecurity-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hipaa-audit .cursor/skills/hipaa-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hipaa-audit" agent skill from https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-audit into .cursor/skills/hipaa-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hipaa-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/briiirussell/cybersecurity-skills.git --path skills/hipaa-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install briiirussell/cybersecurity-skills hipaa-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/briiirussell/cybersecurity-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hipaa-audit .gemini/skills/hipaa-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hipaa-audit" agent skill from https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-audit into .gemini/skills/hipaa-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hipaa-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install briiirussell/cybersecurity-skills hipaa-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/briiirussell/cybersecurity-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hipaa-audit .github/skills/hipaa-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hipaa-audit" agent skill from https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-audit into .github/skills/hipaa-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hipaa-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install briiirussell/cybersecurity-skills hipaa-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/briiirussell/cybersecurity-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hipaa-audit .opencode/skills/hipaa-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hipaa-audit" agent skill from https://github.com/briiirussell/cybersecurity-skills/tree/main/skills/hipaa-audit into .opencode/skills/hipaa-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hipaa-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
hipaa-auditAudit applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule…
Hipaa Audit is an agent skill from briiirussell/cybersecurity-skills. Audit applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule, plus HITECH. Covers ePHI scoping, the 18 HIPAA identifiers, Business Associate Agreement (BAA) chain-of-liability, minimum-necessary standard, and breach notification timing. Use when the user mentions 'HIPAA,' 'HIPAA Security Rule,' 'HIPAA Privacy Rule,' 'PHI,' 'ePHI,' 'protected health information,' 'BAA,' 'business…
Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Legal & Compliance, covering Healthcare and finance regulation. The repository describes itself as: Cybersecurity skills for AI coding agents (Claude Code, Cursor, Codex). The licence is MIT.
12 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c9ade03. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlobBashWriteWebSearchFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Hipaa Audit loads about 4.4k tokens when it runs. Until then it costs about 192 tokens; SKILL.md has 1,960 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Grep, Glob, Bash, Write, WebSearchAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from briiirussell/cybersecurity-skills at commit c9ade03, republished under its MIT licence (© briiirussell). 1,960 words, ~4,425 tokens.
.claude/skills/hipaa-audit/SKILL.md (or your agent's skills folder).HIPAA governs how Protected Health Information (PHI) is handled in the United States healthcare ecosystem. The engineering surface area is large because PHI is broader than people often realize: a calendar entry naming a patient's appointment is PHI; an IP address logged on a portal accessed by a patient may be PHI in combination with a health condition.
The skill is structured around the four HIPAA rules with emphasis on the Security Rule's three safeguard categories (Administrative / Physical / Technical) — that's where engineering work happens. Privacy Rule, Breach Notification Rule, and HITECH layer on top.
Final compliance determinations stay with counsel and your privacy officer; this skill is the technical engineering layer.
Cross-references: privacy-engineering for the GDPR / CCPA-shaped privacy work that often overlaps; iam-audit for access control and authentication; crypto-audit for encryption-at-rest and in-transit detail; secrets-audit for key management; siem-detection for audit-log engineering; incident-triage and security-comms for breach response.
If a system handles PHI for a CE without a BAA, that's a violation regardless of how secure the handling is.
PHI = individually identifiable health information held or transmitted by a CE or BA. ePHI = the electronic form.
The 18 HIPAA identifiers (Safe Harbor de-identification list — if all are stripped, data is no longer PHI):
Important: removing the 18 identifiers via Safe Harbor is one of two de-identification methods. The other is Expert Determination (statistical analysis confirming low re-identification risk). De-identified data is not PHI; pseudonymized data is still PHI (because the key linking the surrogate back to the individual is still held somewhere).
The most common scope reductions:
These are policy and program controls. Engineering teams contribute artifacts; the privacy officer owns the program.
incident-triageEngineering audit input: evidence packages for risk analysis (asset inventory, threat model, controls list), workforce-security records (access reviews, joiner/mover/leaver evidence), training completion records.
For modern SaaS, most physical safeguards are inherited from the cloud provider's compliance posture (covered by the cloud's BAA). Verify:
Engineering audit input: confirm cloud provider's BAA covers the relevant physical-safeguard obligations; confirm workstation disk encryption and remote-wipe for any employee laptop touching ePHI.
This is where this skill spends its time.
Audit grep patterns:
SELECT.*patient, SELECT.*encounter from non-individual accountsIn practice: every read, every write, every access decision involving ePHI logged. Logs preserved for at least 6 years (HIPAA's general document-retention period). See siem-detection for the engineering implementation.
See iam-audit for implementation.
See crypto-audit.
The Privacy Rule sets the rules for how PHI is used and disclosed. The Security Rule says "protect it"; the Privacy Rule says "you can only use it for these specific purposes."
Engineering-relevant slices:
SELECT * from patient tables), API contracts that return only the fields the caller needsAudit grep patterns:
SELECT \*.*patient, SELECT \*.*encounter, SELECT \*.*observation — almost always a minimum-necessary violationA breach is the unauthorized acquisition, access, use, or disclosure of unsecured PHI that compromises the security or privacy of the PHI. "Unsecured" = not encrypted per HHS guidance (encryption is the safe harbor).
Notification timing:
| Recipient | Timing |
|---|---|
| Affected individuals | Without unreasonable delay, no later than 60 calendar days after discovery |
| Department of Health and Human Services (HHS / OCR) | Within 60 days of discovery for breaches affecting ≥ 500 individuals; annually for breaches < 500 |
| Media | Same 60-day window for breaches affecting > 500 in a state or jurisdiction |
| Business associate to covered entity | Without unreasonable delay, no later than 60 days |
A "breach" includes the unauthorized access — not just exfiltration. If a workforce member views a record they had no need to view, that is a breach (unless one of the limited exceptions applies).
Engineering hook: ability to scope a breach quickly. Audit logs (Security Rule §164.312(b)) are the source of truth. Time-to-scope directly impacts the 60-day clock.
Safe harbor: if the PHI was encrypted per HHS-recognized standards (and the key wasn't also compromised), the unauthorized acquisition may not be a breach. This is the strongest reason to encrypt ePHI at rest comprehensively.
See incident-triage (response), security-comms (notification draft — legal review required), breach-patterns (post-incident pattern extraction).
HITECH (2009) strengthened HIPAA in several ways relevant here:
For modern engineering work, HITECH means: a BA that handles ePHI is subject to most of the Security Rule directly. Vendors cannot hide behind the CE.
# HIPAA Audit Findings
## Entity: [name]
## Entity type: Covered Entity / Business Associate / Subcontractor
## Date: [date]
## Auditor: [name]
### Scope
- [ ] ePHI inventory complete (every data store containing PHI)
- [ ] Data flow diagrams for PHI transmission paths
- [ ] BAA in place with every BA (and BA's subcontractors where required)
- [ ] Cloud provider BAA on file (AWS / GCP / Azure / etc.)
- [ ] Risk analysis (§164.308(a)(1)(ii)(A)) current
### Administrative safeguards
| Subsection | Status | Findings |
|------------|--------|----------|
| Security Management Process | | |
| Assigned Security Responsibility | | |
| Workforce Security | | |
| Information Access Management | | |
| Security Awareness and Training | | |
| Security Incident Procedures | | |
| Contingency Plan | | |
| Evaluation | | |
| BA Contracts | | |
### Technical safeguards
| Subsection | Status | Findings |
|------------|--------|----------|
| Access Control — unique IDs | | |
| Access Control — emergency access | | |
| Access Control — automatic logoff | | |
| Access Control — encryption at rest | | |
| Audit Controls | | |
| Integrity | | |
| Person / Entity Authentication (MFA) | | |
| Transmission Security (encryption in transit) | | |
### Privacy Rule
- [ ] Minimum necessary applied in code (no SELECT * on PHI tables)
- [ ] Notice of Privacy Practices published and presented
- [ ] Individual access path implemented (30-day delivery)
- [ ] Amendment / accounting of disclosures process exists
### Breach response readiness
- [ ] Audit logs sufficient to scope a breach within 60-day clock
- [ ] Incident-response procedures tested
- [ ] Notification templates drafted (see security-comms)
- [ ] Encryption-as-safe-harbor verified across ePHI stores
### Findings detail
[Per finding: section reference, severity, location, evidence, remediation]
### Recommendations
[Prioritized]Disposition rule (Fixed / Deferred / Accepted Risk) per owasp-audit. HIPAA accepted-risk is highly disfavored — most "accepted risks" should be documented as residual risk with compensating controls and re-evaluation triggers.
SELECT * on PHI tables — minimum-necessary violation; API serializers returning all fields when callers need fewsecurity-comms and counselhhs.gov/hipaa (regulatory text, FAQs, OCR resolution agreements)© briiirussell, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/hipaa-audit of briiirussell/cybersecurity-skills.
Open the folder on GitHubat commit c9ade03
Hipaa Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hipaa Audit this skillbriiirussell/cybersecurity-skills | 413 | — | ~4.4k | Automated safety check: Notes | MIT | |
| HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed | 5.5k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| HIPAA Pre-Deployment Compliance Checkmaziyarpanahi/openmed | 5.5k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Hipaa ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance | 946 | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| ISO Standards Readiness EvidenceK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~4.6k | Automated safety check: Notes | MIT | |
| Fda Consultant Specialistdavila7/claude-code-templates | 33k | 1 repos | ~2.7k | Automated safety check: Pass | MIT |
maziyarpanahi/openmed
Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.
maziyarpanahi/openmed
Walks a data pipeline against the HIPAA Privacy and Security Rule checklist and produces a gap report before it processes patient data.
Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
Expert HIPAA compliance assistant for healthcare and software contexts.
K-Dense-AI/scientific-agent-skills
Organizes scope, controlled documents, risk files and traceability into draft evidence for human review against ISO 13485, 14971, 17025 and 15189.
davila7/claude-code-templates
Senior FDA consultant and specialist for medical device companies including HIPAA compliance and requirement management.
mlunato47/claude-grc-plugin
Senior GRC analyst expertise across 18 compliance frameworks — NIST 800-53, FedRAMP (Rev5 + 20x/CR26, KSIs, VDR/VER, Certification Classes A–D), DoD/DoW Impact Levels (IL2–IL6, DISA Cloud SRG), ITAR…
briiirussell/cybersecurity-skills
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency…
briiirussell/cybersecurity-skills
Audit REST, GraphQL, and RPC APIs against the OWASP API Security Top 10 (2023).
briiirussell/cybersecurity-skills
Learn from public breach disclosures — extract the audit question each one implies and check your own stack.
briiirussell/cybersecurity-skills
Audit cloud infrastructure (AWS, GCP, Azure) for misconfigurations, excessive permissions, and security gaps.
briiirussell/cybersecurity-skills
Audit container images, Dockerfiles, and Kubernetes manifests for misconfigurations, excessive privileges, exposed secrets, and runtime risks.
briiirussell/cybersecurity-skills
Audit cryptography implementation — algorithm choice, key sizes, KDF parameters, IV/nonce handling, signature verification, randomness, TLS configuration, and key rotation.
Categories
Audit applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule…. Hipaa Audit is an agent skill from briiirussell/cybersecurity-skills. Audit applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule, plus HITECH.
Hipaa Audit fits situations like: the user mentions HIPAA; HIPAA Security Rule; HIPAA Privacy Rule; protected health information.
Run `npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a claude-code`. Or copy the skill folder (skills/hipaa-audit in briiirussell/cybersecurity-skills) into .claude/skills/hipaa-audit in your project. Claude Code loads it when a task matches its description.
Run `npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a codex`. Or copy the skill folder (skills/hipaa-audit in briiirussell/cybersecurity-skills) into .agents/skills/hipaa-audit in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add briiirussell/cybersecurity-skills --skill hipaa-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hipaa-audit, .gemini/skills/hipaa-audit, .github/skills/hipaa-audit and .opencode/skills/hipaa-audit in your project.
SKILL.md names no scripts, command-line tools or credentials: Hipaa Audit is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash, Write, WebSearch.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Hipaa Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Hipaa Audit: HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars), HIPAA Pre-Deployment Compliance Check (maziyarpanahi/openmed, 5.5k stars), Hipaa Compliance (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 946 stars) and ISO Standards Readiness Evidence (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
briiirussell (a GitHub user) maintains it in briiirussell/cybersecurity-skills, which has 413 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on May 27, 2026.
Source: briiirussell/cybersecurity-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.