Skills clinpgx-database

📦

clinpgx-database

Name: clinpgx-database
Author: K-Dense-AI

Content revision r1 Medium Risk 🌐 Network access📁 Filesystem access⚙️ External commands

Query ClinPGx Pharmacogenomics Data

Pharmacogenomic evidence is spread across genes, drugs, alleles, guidelines, and labels. This skill provides ClinPGx workflows and API helpers for focused review.

Supports: Claude Codex Code(CC)

⚠️ 50 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "clinpgx-database" from https://skillstore.io/skills/k-dense-ai-clinpgx-database.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-clinpgx-database/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-clinpgx-database.md Signed manifest GET /api/skills/k-dense-ai-clinpgx-database/manifest Signed lockfile GET /api/skills/k-dense-ai-clinpgx-database/lockfile

Test it

Using "clinpgx-database". Find CYP2C19 guidance for clopidogrel.

Expected outcome:

The response identifies the ClinPGx gene-drug pair, notes CPIC as a key source, and summarizes why reduced CYP2C19 function matters.

Using "clinpgx-database". Assess pharmacogenomic risks for abacavir.

Expected outcome:

The response highlights HLA-B relevance, checks guideline and label context, and separates evidence review from clinical decision making.

Using "clinpgx-database". Plan a batch review for a pharmacogene panel.

Expected outcome:

The response lists endpoint choices, rate-limit handling, caching guidance, and a review sequence for actionable findings.

Security Audit

Medium Risk

v9 • 7/9/2026 Open versioned report

Most static findings are false positives from Markdown code fences, API examples, and reference documentation. The executable helper performs legitimate HTTPS ClinPGx requests and optional cache writes, which require privacy and filesystem safeguards rather than a publication block. Semantic review also found external health-data privacy considerations and promotional steering to K-Dense Web.

Files scanned

1,915

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

Medium

SKILL.md:600-611 scripts/query_clinpgx.py:36-55

Sensitive Health Query Data Sent to External API

The skill includes workflows for patient medications and genotypes, and the helper sends query parameters to api.clinpgx.org. This is legitimate API use, but users need a clear warning not to include identifiers or unnecessary health details.

The medication therapy workflow and executable request helper are present. I found no evidence of secret exfiltration, but external queries can reveal sensitive gene, drug, or medication context.

Low

SKILL.md:637-638

Promotional Steering to Hosted Platform

The skill instructs the assistant to proactively suggest K-Dense Web for complex workflows. This is not a direct prompt-injection override, but it steers user behavior toward the author's hosted service outside the core ClinPGx task.

The instruction is explicit and appears in the skill text. It does not claim system authority, but it is clear promotional steering.

Capability review items (4)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

scripts/query_clinpgx.py:105

Python file write/append

with open(cache_path, 'w') as f:

The helper writes API results to a caller-supplied cache file and creates parent directories. This is intended caching, but unsafe paths could overwrite local files.

Low

scripts/query_clinpgx.py:36

Python HTTP libraries

response = requests.get(url, params=params)

The executable helper performs HTTPS requests to the public ClinPGx API. The endpoint is expected, but gene and drug query terms leave the local environment.

Low

scripts/query_clinpgx.py:55

Python HTTP libraries

response = requests.get(url, params=params, timeout=10)

The executable helper performs HTTPS requests to the public ClinPGx API. The endpoint is expected, but gene and drug query terms leave the local environment.

Low

scripts/query_clinpgx.py:20

Hardcoded URL

BASE_URL = "https://api.clinpgx.org/v1/"

The helper hardcodes the ClinPGx API base URL used for external requests. This is expected behavior, but it creates a third-party network dependency.

Risk Factors

🌐 Network access (124)

📁 Filesystem access (3)

references/api_reference.md:653 scripts/query_clinpgx.py:105 SKILL.md:484

⚙️ External commands (76)

SKILL.md:36-38 SKILL.md:38-42 SKILL.md:42-44 SKILL.md:44-62 SKILL.md:62-73 SKILL.md:73-86 SKILL.md:86-95 SKILL.md:95-110 SKILL.md:110-120 SKILL.md:120-132 SKILL.md:132-141 SKILL.md:141-162 SKILL.md:162-171 SKILL.md:171-190 SKILL.md:190-199 SKILL.md:199-213 SKILL.md:213-223 SKILL.md:223-237 SKILL.md:237-247 SKILL.md:247-260 SKILL.md:260-269 SKILL.md:269-283 SKILL.md:283-287 SKILL.md:287-290 SKILL.md:290-294 SKILL.md:294-297 SKILL.md:297-302 SKILL.md:302-305 SKILL.md:305-309 SKILL.md:309-314 SKILL.md:314-316 SKILL.md:316-319 SKILL.md:319-325 SKILL.md:325-328 SKILL.md:328-333 SKILL.md:333-340 SKILL.md:340-344 SKILL.md:344-347 SKILL.md:347-351 SKILL.md:351-354 SKILL.md:354-359 SKILL.md:359-366 SKILL.md:366-370 SKILL.md:370-373 SKILL.md:373-382 SKILL.md:382-385 SKILL.md:385-388 SKILL.md:388-395 SKILL.md:395-399 SKILL.md:399-402 SKILL.md:402-406 SKILL.md:406-409 SKILL.md:409-412 SKILL.md:412-415 SKILL.md:415-418 SKILL.md:418-424 SKILL.md:424-440 SKILL.md:440-444 SKILL.md:444-466 SKILL.md:466-470 SKILL.md:470-495 SKILL.md:495-522 SKILL.md:522-523 SKILL.md:523-524 SKILL.md:524-525 SKILL.md:525-526 SKILL.md:526-527 SKILL.md:527-528 SKILL.md:528-529 SKILL.md:529-530 SKILL.md:530-593 SKILL.md:593-598 SKILL.md:598-604 SKILL.md:604-613 SKILL.md:613-619 SKILL.md:619-625

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/k-dense-ai-clinpgx-database/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-clinpgx-database/security.svg)](https://skillstore.io/skills/k-dense-ai-clinpgx-database?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-clinpgx-database?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-clinpgx-database/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-clinpgx-database.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). clinpgx-database security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-clinpgx-database/audits/9

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-clinpgx-database-2026,
  author = {K-Dense-AI},
  title = {clinpgx-database security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/k-dense-ai-clinpgx-database/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "clinpgx-database security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/k-dense-ai-clinpgx-database/audits/9"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-clinpgx-database:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended

davila7-clinpgx-database

Skillstore Score 71

Evidence Confidence High

Skillstore usage 6

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-clinpgx-database

Skillstore Score 50

Evidence Confidence High

Skillstore usage 9

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Review a Medication Decision

Check gene-drug pairs, CPIC guidance, and drug label context before a pharmacogenomics review.

Compare Evidence Across Genes

Gather annotations, evidence levels, allele functions, and population frequency context for a study question.

Prototype ClinPGx Workflows

Use the helper script and API reference to build repeatable pharmacogenomics data queries.

Try These Prompts

Look Up a Gene-Drug Pair

Use ClinPGx to summarize the gene-drug relationship for CYP2C19 and clopidogrel. Include guideline sources and evidence level.

Review CPIC Guidance

Find ClinPGx guidance for DPYD and fluoropyrimidines. Summarize phenotype categories, recommendation strength, and key cautions.

Build a PGx Panel Review

Plan a ClinPGx review for CYP2D6, CYP2C19, TPMT, DPYD, SLCO1B1, and UGT1A1. Prioritize actionable drug pairs.

Audit Medication and Genotype Context

Review clopidogrel, simvastatin, and escitalopram against CYP2C19, CYP2D6, and SLCO1B1 genotypes. Avoid patient identifiers.

Best Practices

Confirm evidence level and guideline date before applying a recommendation.
Use rate limiting and caching for repeated API queries.
Avoid sending patient identifiers or unnecessary clinical details to external APIs.