Skills fda-database

📦

fda-database

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

Content revision r1 Low Risk 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Query FDA Regulatory Databases

FDA data is spread across many specialized endpoints. This skill guides safe openFDA queries for research, surveillance, and regulatory review.

Supports: Claude Codex Code(CC)

📊 76 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 "fda-database" from https://skillstore.io/skills/k-dense-ai-fda-database.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-fda-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-fda-database.md Signed manifest GET /api/skills/k-dense-ai-fda-database/manifest Signed lockfile GET /api/skills/k-dense-ai-fda-database/lockfile

Test it

Using "fda-database". Find safety signals for aspirin.

Expected outcome:

A concise safety profile with event volume, top reported reactions, serious event count, recent recalls, and endpoint notes.

Using "fda-database". Monitor Class I food recalls for undeclared peanut.

Expected outcome:

A grouped recall summary showing affected products, recall reasons, dates, firm names, statuses, and public data limitations.

Using "fda-database". Compare pacemaker adverse events and recalls.

Expected outcome:

A device surveillance summary with event types, recent reports, recall records, classification context, and recommended follow-up queries.

Security Audit

Low Risk

v7 • 7/5/2026 Open versioned report

This skill provides openFDA query guidance and Python helpers for public FDA datasets. Static matches for network calls, API key handling, cache writes, and markdown backticks are consistent with the stated function. A low-severity semantic issue remains because SKILL.md includes a product-promotion instruction for K-Dense Web.

Files scanned

4,513

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:517-518

Embedded Product Promotion Instruction

SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users toward the author platform outside the core FDA data task.

The instruction is explicit and located in the skill guidance. I found no evidence that it bypasses security review or asks the model to ignore higher-priority instructions.

Risk Factors

🌐 Network access (113)

🔑 Env variables (138)

📁 Filesystem access (2)

references/api_basics.md:569 scripts/fda_query.py:80

⚙️ External commands (59)

SKILL.md:40-56 SKILL.md:56-67 SKILL.md:67-69 SKILL.md:69-73 SKILL.md:73-84 SKILL.md:84-101 SKILL.md:101-116 SKILL.md:116-118 SKILL.md:118-136 SKILL.md:136-149 SKILL.md:149-151 SKILL.md:151-162 SKILL.md:162-174 SKILL.md:174-176 SKILL.md:176-186 SKILL.md:186-196 SKILL.md:196-198 SKILL.md:198-209 SKILL.md:209-219 SKILL.md:219-221 SKILL.md:221-229 SKILL.md:229-259 SKILL.md:259-265 SKILL.md:265-288 SKILL.md:288-294 SKILL.md:294-317 SKILL.md:317-323 SKILL.md:323-335 SKILL.md:335-343 SKILL.md:343-357 SKILL.md:357-363 SKILL.md:363-375 SKILL.md:375-381 SKILL.md:381-396 SKILL.md:396-403 SKILL.md:403-406 SKILL.md:406-409 SKILL.md:409-412 SKILL.md:412-416 SKILL.md:416-422 SKILL.md:422-424 SKILL.md:424-427 SKILL.md:427-431 SKILL.md:431-433 SKILL.md:433-439 SKILL.md:439-445 SKILL.md:445-451 SKILL.md:451-456 SKILL.md:456-457 SKILL.md:457-458 SKILL.md:458-459 SKILL.md:459-460 SKILL.md:460-461 SKILL.md:461-465 SKILL.md:465-467 SKILL.md:467-473 SKILL.md:473-484 SKILL.md:484-486 SKILL.md:486-507

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-fda-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-fda-database/security.svg)](https://skillstore.io/skills/k-dense-ai-fda-database?utm_source=security_passport_badge)

HTML badge

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

Embed card

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

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-fda-database-2026,
  author = {K-Dense-AI},
  title = {fda-database security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-fda-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: "fda-database security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-fda-database/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-fda-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

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended

davila7-fda-database

Skillstore Score 80

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-fda-database

Skillstore Score 76

Evidence Confidence High

Skillstore usage 16

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Review Drug Safety Signals

Summarize adverse event counts, common reactions, serious reports, labels, and recalls for a selected drug.

Track Device Regulatory History

Find device adverse events, clearances, classifications, PMA records, UDI data, and recall activity.

Monitor Food Recall Risks

Search food enforcement records by allergen, contamination term, classification, status, and recall date.

Try These Prompts

Find Drug Label Information

Use the FDA database skill to find label information for [drug]. Summarize indications, warnings, dosage fields, and the source endpoint.

Check Recent Recalls

Search openFDA recalls for [product or ingredient]. Group results by classification, reason, status, and recall initiation date.

Compare Safety Profiles

Compare adverse event profiles for [drug A], [drug B], and [drug C]. Include total reports, serious reports, and common reactions.

Build Regulatory Review

Create a cross-database FDA review for [product]. Combine events, labels, approvals, recalls, identifiers, and data quality caveats.

Best Practices

Use precise field searches before broad wildcard searches.
Set FDA_API_KEY for higher limits when running repeated analyses.
Document endpoint names, query terms, dates, and known missing fields in every result summary.

Avoid

Do not treat adverse event counts as incidence rates without denominator data.
Do not make clinical or legal conclusions from openFDA records alone.
Do not run broad paginated searches without rate limits, caps, and a clear purpose.