Home / Plugins / healthclaw-guardrails
healthclaw-guardrails
aks129/HealthClawGuardrailsPlugin
HealthClaw Guardrails is the security layer between AI agents and clinical FHIR data. Every agent read passes through PHI redaction (names truncated to initials, DOBs to year, identifiers masked). Every write requires an HMAC-signed step-up token with a 5-minute TTL. Clinical writes (Condition, MedicationRequest, DiagnosticReport) return HTTP 428 until a human confirms. Every access lands in an append-only audit trail scoped by tenant. Supports FHIR R4 US Core v9 (stable) and FHIR R6 v6.0.0-ballot3 (experimental). Proxies upstream FHIR servers (HAPI, Epic sandbox, Medplum via OAuth2 client-credentials, SMART Health IT) so the same guardrails apply whether you're on local SQLite or production EHRs. Bundled skills: fhir-r6-guardrails (core MCP + 14 tools), curatr (patient-facing data-quality evaluation and correction), fasten-connect (patient-authorized EHR ingestion + TEFCA), phi-redaction (HIPAA Safe Harbor de-identification), fhir-upstream-proxy (vendor-neutral server proxy), healthex-export (portable health record export).
Why this score
Popularity score: 66/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 22, 2026 at commit bb315afc54e5, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.
What its code does:
- Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.app.py, openclaw/bot.py, r6/actions/rails/__init__.py and 29 more
- Runs shell commands Common for dev tools. Read the commands it runs.scripts/check_table_stakes.py:315, scripts/demo_e2e.sh:245 and 1 more
- Runs code it builds while running (eval or exec) Harder to read ahead of time, since the code is assembled while it runs.r6/rate_limit.py:211
- Makes network requestsapp.py:445, careagents/healthcheck.py:21, careagents/llm.py:224 and 78 more
Web addresses in its code:
- hl7.orgr6/access.py:690
- loinc.orgcareagents/labs_timeline.py:25
- terminology.hl7.orgr6/curatr.py:1043
- healthclaw.ioapp.py:146
- app.healthclaw.ioapi/index.py:25
- oauth.app.healthbankone.comscripts/healthbankone_oauth.py:9
- snomed.infor6/curatr.py:71
- fhir.medent.comscripts/export_medent_fhir.py:28
- unitsofmeasure.orgr6/routes.py:2723
- nlm.nih.govr6/curatr.py:75
- api.resend.comapp.py:353
- api.healthex.ioscripts/export_healthex_legacy.py:23
- careagents.clouddeploy/careagents/deploy.sh:59
- api.telegram.orgopenclaw/bot.py:865
- mcp.app.healthbankone.comopenclaw/bot.py:108
And 27 more.
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onehealthclaw-guardrails aks129/HealthClawGuardrails · Plugin | 66 | ★ 31 | not measured | yesterday |
| guardrail-tester RyanAlberts/best-of-Agent-Harnesses · Skill Both about guardrail | 69 | ★ 1.3k | ≈22 always | 17d ago |
| speclock-guardrails sgroy10/speclock · Skill Both about guardrail | 56 | ★ 25 | ≈65 always | 3mo ago |
| sdlc-guardrails TsCarpe/claude-sdlc-skills · Skill Both about guardrail and require | 56 | ★ 64 | ≈136 always | 17d ago |
| guardrail-runner climate-federation/legoESM · Subagent Both about guardrail | 62 | ★ 138 | ≈143 in chat | 16d ago |
| ai-coding-guardrails OneWave-AI/claude-skills · Skill Both about guardrail | 65 | ★ 355 | ≈107 always | 16d ago |