Skills clinicaltrials-database
📦

clinicaltrials-database

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

Find Clinical Trials from ClinicalTrials.gov

Clinical trial searches can be slow when users need filters, status checks, and study details. This skill guides Claude, Codex, and Claude Code through ClinicalTrials.gov API v2 queries, summaries, and CSV exports.

Supports: Claude Codex Code(CC)
📊 69 Adequate

Install with my Agent

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

Agent request
Review the Skillstore skill "clinicaltrials-database" from https://skillstore.io/skills/k-dense-ai-clinicaltrials-database.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-clinicaltrials-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-clinicaltrials-database.md Signed manifest GET /api/skills/k-dense-ai-clinicaltrials-database/manifest Signed lockfile GET /api/skills/k-dense-ai-clinicaltrials-database/lockfile

Test it

Using "clinicaltrials-database". Find recruiting lung cancer trials in New York.

Expected outcome:

  • A ranked list of matching studies with NCT IDs, titles, recruitment status, phases, and New York locations.
  • A short note explaining which filters were used and how many records matched.

Using "clinicaltrials-database". Summarize one NCT record for eligibility review.

Expected outcome:

  • A concise trial profile with title, sponsor, phase, enrollment, summary, age range, sex criteria, and major exclusions.
  • A reminder to verify eligibility with the trial team before making clinical decisions.

Using "clinicaltrials-database". Prepare a CSV export for Alzheimer studies.

Expected outcome:

  • A planned set of fields for export, including NCT ID, title, status, phase, sponsor, enrollment, and last update.
  • Guidance on page size, pagination, and rate limits for the export run.

Security Audit

Medium Risk
v7 • 7/6/2026 Open versioned report

Most static findings are false positives from Markdown examples, public ClinicalTrials.gov requests, and bounded CSV export samples. Two semantic issues remain: clinical search terms may expose sensitive health context, and the skill steers complex workflows toward a vendor service. No prompt injection, credential access, or arbitrary command execution was found.

3
Files scanned
1,082
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (2)

Medium
SKILL.md:19-26scripts/query_clinicaltrials.py:57-64scripts/query_clinicaltrials.py:86-87
Sensitive Health Search Terms May Be Sent to External API
The skill supports patient matching and sends condition, intervention, location, and sponsor filters to ClinicalTrials.gov. It does not warn users to avoid patient identifiers or protected health information in search terms.
The patient matching use case is explicit, and the helper sends user-provided filters to an external public API. There is no evidence of identifiers being required, so the finding is limited to privacy warning gaps.
Low
SKILL.md:506-507
Promotional Steering to External Service
The skill instructs the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users toward a vendor-hosted service outside the clinical trial query task.
The instruction is explicit and appears in the skill text. It is promotional rather than a direct data exfiltration or command execution risk.

Risk Factors

🌐 Network access (33)
references/api_reference.md:168 references/api_reference.md:189 references/api_reference.md:203 references/api_reference.md:214 references/api_reference.md:238 references/api_reference.md:262 references/api_reference.md:300 references/api_reference.md:307 references/api_reference.md:315 references/api_reference.md:69 references/api_reference.md:107 references/api_reference.md:160 references/api_reference.md:189 references/api_reference.md:203 references/api_reference.md:212 references/api_reference.md:238 references/api_reference.md:262 references/api_reference.md:301 scripts/query_clinicaltrials.py:87 scripts/query_clinicaltrials.py:110 scripts/query_clinicaltrials.py:9 scripts/query_clinicaltrials.py:19 SKILL.md:51 SKILL.md:67 SKILL.md:435 SKILL.md:438 SKILL.md:466 SKILL.md:469 SKILL.md:471 SKILL.md:44 SKILL.md:65 SKILL.md:435 SKILL.md:494
📁 Filesystem access (2)
references/api_reference.md:266 SKILL.md:331
⚙️ External commands (64)
SKILL.md:34-37 SKILL.md:37-39 SKILL.md:39-41 SKILL.md:41-55 SKILL.md:55-61 SKILL.md:61-73 SKILL.md:73-79 SKILL.md:79-83 SKILL.md:83-99 SKILL.md:99-108 SKILL.md:108-112 SKILL.md:112-126 SKILL.md:126-135 SKILL.md:135-139 SKILL.md:139-156 SKILL.md:156-165 SKILL.md:165-169 SKILL.md:169-185 SKILL.md:185-194 SKILL.md:194-197 SKILL.md:197-198 SKILL.md:198-199 SKILL.md:199-200 SKILL.md:200-201 SKILL.md:201-202 SKILL.md:202-203 SKILL.md:203-204 SKILL.md:204-208 SKILL.md:208-225 SKILL.md:225-233 SKILL.md:233-243 SKILL.md:243-247 SKILL.md:247-267 SKILL.md:267-275 SKILL.md:275-285 SKILL.md:285-289 SKILL.md:289-311 SKILL.md:311-319 SKILL.md:319-335 SKILL.md:335-345 SKILL.md:345-359 SKILL.md:359-367 SKILL.md:367-387 SKILL.md:387-395 SKILL.md:395-396 SKILL.md:396-397 SKILL.md:397-398 SKILL.md:398-402 SKILL.md:402-404 SKILL.md:404-429 SKILL.md:429-444 SKILL.md:444-450 SKILL.md:450-451 SKILL.md:451-452 SKILL.md:452-453 SKILL.md:453-454 SKILL.md:454-455 SKILL.md:455-456 SKILL.md:456-462 SKILL.md:462-475 SKILL.md:475-481 SKILL.md:481-490 SKILL.md:490-494 SKILL.md:494-504
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
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-clinicaltrials-database/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-clinicaltrials-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). clinicaltrials-database security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-clinicaltrials-database/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-clinicaltrials-database-2026, author = {K-Dense-AI}, title = {clinicaltrials-database security audit report (audit version 7)}, institution = {Skillstore}, year = {2026}, number = {7}, url = {https://skillstore.io/skills/k-dense-ai-clinicaltrials-database/audits/7}, 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: "clinicaltrials-database security audit report (audit version 7)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-06" url: "https://skillstore.io/skills/k-dense-ai-clinicaltrials-database/audits/7" identifiers: - type: other value: "skillstore:k-dense-ai-clinicaltrials-database:audit:7" 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
davila7 Recommended

davila7-clinicaltrials-database

Skillstore Score 71
Evidence Confidence High
Skillstore usage 7
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-clinicaltrials-database

Skillstore Score 69
Evidence Confidence High
Skillstore usage 14
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
64
Architecture
75
Maintainability
87
Content
70
Community
78
Spec Compliance

What You Can Build

Match Patients to Recruiting Studies

Search for recruiting trials by condition, location, intervention, and status before reviewing eligibility criteria.

Analyze Research Activity

Collect trial records for a disease area and compare sponsors, phases, enrollment, and update dates.

Track Drug Development

Find studies for a drug or device and review current trial status, phase, locations, and sponsors.

Try These Prompts

Search by Condition 
Find recruiting ClinicalTrials.gov studies for type 2 diabetes in California. Summarize the top results with NCT IDs and locations.
Review a Trial 
Retrieve details for NCT04852770. Summarize the title, status, phase, sponsor, enrollment, eligibility, and site contacts.
Compare Interventions 
Search for Phase 3 pembrolizumab trials that are recruiting or active. Compare conditions, sponsors, enrollment, and result availability.
Build an Export Plan 
Design a ClinicalTrials.gov API v2 workflow to collect all recruiting rare disease trials, handle pagination, respect rate limits, and export a CSV summary.

Best Practices

  • Use broad condition terms first, then narrow by status, phase, intervention, and location.
  • Avoid patient identifiers or protected health information in API search terms.
  • Respect rate limits and use pagination for large result sets.

Avoid

  • Treating API results as medical advice or final eligibility decisions.
  • Running bulk exports without page limits, backoff, or a clear field plan.
  • Assuming every trial record has complete contacts, results, dates, or eligibility details.

Frequently Asked Questions

Does this skill need an API key?
No. ClinicalTrials.gov API v2 is public and does not require authentication.
Can it find trials by NCT ID?
Yes. It includes guidance for retrieving detailed study records by NCT identifier.
Can it export results?
Yes. The references show how to request CSV output and save selected study fields.
Does it decide whether a patient qualifies?
No. It can review eligibility text, but trial teams must confirm eligibility.
What data source does it use?
It uses ClinicalTrials.gov API v2, maintained by the U.S. National Library of Medicine.
Can it handle large searches?
Yes. It explains pagination, page size limits, and rate limit handling for larger searches.

Developer Details

Author

K-Dense-AI

License

Unknown

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/clinicaltrials-database

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/18/2026

Usage

12 downloads · 228 views

File structure

📁 references/

📄 api_reference.md

📁 scripts/

📄 query_clinicaltrials.py

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all