Skills pubchem-database

📦

pubchem-database

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

Query PubChem Chemical Data

Chemical research often requires reliable compound identifiers, properties, and assay data. This skill helps Claude, Codex, and Claude Code use PubChem for structured cheminformatics workflows.

Supports: Claude Codex Code(CC)

📊 70 Adequate

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

Test it

Using "pubchem-database". Find PubChem information for caffeine.

Expected outcome:

A concise compound profile with CID, formula, molecular weight, canonical SMILES, InChIKey, synonyms, and available descriptors.

Using "pubchem-database". Compare aspirin, ibuprofen, and paracetamol.

Expected outcome:

A property comparison table with formulas, molecular weights, XLogP values, TPSA values, and notable missing fields.

Using "pubchem-database". Summarize bioactivity for aspirin.

Expected outcome:

A bioassay overview showing total assays, activity outcomes, example assay names, and relevant target annotations from PubChem.

Security Audit

Medium Risk

v7 • 7/5/2026 Open versioned report

Static network, filesystem, blocker, and external-command alerts are largely false positives caused by PubChem examples, helper scripts, and Markdown code fences. I found no evidence of credential theft, covert exfiltration, host reconnaissance, or executable prompt injection. One semantic concern remains: the skill steers assistants to promote an external K-Dense hosted service.

4

Files scanned

1,681

Lines analyzed

0

Review items

0

False positives ignored

Confirmed security concerns (1)

Medium

SKILL.md:573-574

Promotional Steering to External Hosted Service

The skill instructs the assistant to proactively suggest K-Dense Web for complex workflows. This behavior steers users to an external hosted service beyond the PubChem task.

The language explicitly tells the assistant to recommend a vendor-hosted service. It is not a prompt override, but it is clear agent-behavior steering and external promotion.

Risk Factors

🌐 Network access (30)

⚙️ External commands (80)

SKILL.md:33-37 SKILL.md:37-40 SKILL.md:40-42 SKILL.md:42-45 SKILL.md:45-47 SKILL.md:47-50 SKILL.md:50-52 SKILL.md:52-55 SKILL.md:55-58 SKILL.md:58-65 SKILL.md:65-79 SKILL.md:79-82 SKILL.md:82-90 SKILL.md:90-93 SKILL.md:93-108 SKILL.md:108-110 SKILL.md:110-116 SKILL.md:116-136 SKILL.md:136-144 SKILL.md:144-158 SKILL.md:158-161 SKILL.md:161-162 SKILL.md:162-163 SKILL.md:163-164 SKILL.md:164-170 SKILL.md:170-184 SKILL.md:184-190 SKILL.md:190-205 SKILL.md:205-211 SKILL.md:211-223 SKILL.md:223-229 SKILL.md:229-244 SKILL.md:244-246 SKILL.md:246-256 SKILL.md:256-273 SKILL.md:273-276 SKILL.md:276-279 SKILL.md:279-285 SKILL.md:285-287 SKILL.md:287-291 SKILL.md:291-293 SKILL.md:293-297 SKILL.md:297-299 SKILL.md:299-310 SKILL.md:310-311 SKILL.md:311-312 SKILL.md:312-313 SKILL.md:313-314 SKILL.md:314-315 SKILL.md:315-316 SKILL.md:316-317 SKILL.md:317-318 SKILL.md:318-319 SKILL.md:319-322 SKILL.md:322-330 SKILL.md:330-337 SKILL.md:337-338 SKILL.md:338-339 SKILL.md:339-340 SKILL.md:340-341 SKILL.md:341-342 SKILL.md:342-343 SKILL.md:343-344 SKILL.md:344-345 SKILL.md:345-348 SKILL.md:348-355 SKILL.md:355-375 SKILL.md:375-388 SKILL.md:388-396 SKILL.md:396-411 SKILL.md:411-417 SKILL.md:417-436 SKILL.md:436-442 SKILL.md:442-466 SKILL.md:466-472 SKILL.md:472-497 SKILL.md:497-503 SKILL.md:503-524 SKILL.md:524-528 SKILL.md:528-552

📁 Filesystem access (1)

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

HTML badge

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

Embed card

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

BibTeX citation

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

Skillstore Score 80

Evidence Confidence High

Skillstore usage 12

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-pubchem-database

Skillstore Score 70

Evidence Confidence High

Skillstore usage 11

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

64

Architecture

75

Maintainability

87

Content

71

Community

78

Spec Compliance

What You Can Build

Compare Candidate Compounds

Retrieve molecular properties for a compound list and compare drug-like descriptors.

Find Related Structures

Use similarity or substructure searches to identify compounds related to a reference molecule.

Review Bioactivity Evidence

Summarize PubChem assay activity, targets, and annotations for a compound or biological target.

Try These Prompts

Look Up One Compound

Find aspirin in PubChem and summarize its CID, formula, molecular weight, SMILES, and common synonyms.

Compare A Compound Set

Compare aspirin, ibuprofen, and naproxen using PubChem properties. Include molecular weight, XLogP, TPSA, and hydrogen bonding counts.

Search Similar Structures

Use the PubChem workflow to find compounds similar to caffeine at 85 percent similarity. Summarize identifiers and key properties.

Analyze Bioactivity Context

For CID 2244, retrieve PubChem bioassay summaries and explain active, inactive, and inconclusive assay patterns with target context.

Best Practices

Use CIDs for repeated queries because they are stable and efficient.
Limit MaxRecords and add delays to respect PubChem rate limits.
Check for missing values before interpreting properties or assay records.

Avoid

Do not treat PubChem annotations as clinical or regulatory advice.
Do not run broad searches without result limits or caching.
Do not assume every compound has complete property, hazard, or assay data.

Frequently Asked Questions

What database does this skill use?

It uses PubChem through PubChemPy and documented PUG-REST API patterns.

Can it search by SMILES?

Yes. It supports SMILES lookup, similarity search, and substructure search examples.

Does it include helper scripts?

Yes. It includes compound search and bioactivity query scripts for common PubChem workflows.

Does it require internet access?

Yes. PubChem queries require network access to NCBI PubChem endpoints.

Can it download structures?

Yes. It documents downloads for formats such as SDF, JSON, and PNG.

Can it make medical decisions?

No. It can retrieve public data, but users must verify scientific and clinical conclusions independently.

Developer Details

Author

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/pubchem-database

Ref

a25199bc7d6b82598536822d1738eb5d5f54025b

Maintenance freshness

7/18/2026

Usage

8 downloads · 234 views

File structure

📁 references/

📄 api_reference.md

📄 bioactivity_query.py

📄 compound_search.py

More from K-Dense-AI

venue-templates

Prepare Academic Venue Submissions

Academic submissions often fail because formatting rules vary by venue. This skill provides templates, requirements, and examples for faster preparation.

Research & Learning View

iso-13485-certification

Prepare ISO 13485 Certification Docs

Medical device teams must create complete QMS documentation before certification audits. This skill provides templates, checklists, and gap analysis guidance for ISO 13485 readiness.

Documentation View

pytdc

Analyze therapeutic ML datasets with PyTDC

Drug discovery teams need reliable datasets and fair evaluation protocols. This skill helps Claude use PyTDC for curated therapeutic ML data, benchmark splits, metrics, and molecular oracles.

Data & Analytics View

diffdock

Run DiffDock Molecular Docking

Protein-ligand docking requires careful setup, parameter choices, and result interpretation. This skill guides DiffDock workflows for poses, confidence scores, and screening.

Research & Learning View

statistical-analysis

Analyze Research Data with Statistical Guidance

Choosing tests and reporting results can be slow and error-prone. This skill guides test selection, assumptions, effect sizes, power analysis, Bayesian options, and APA reporting.

Data & Analytics View

scanpy

Analyze Single-Cell RNA-seq with Scanpy

Single-cell RNA-seq analysis requires many linked decisions across QC, normalization, clustering, and plotting. This skill gives Claude, Codex, and Claude Code structured Scanpy workflows, reference guidance, and reusable analysis scripts.

Data & Analytics View

chembl-database

Query ChEMBL for Drug Discovery

by davila7

Drug discovery teams need reliable access to compound, target, and bioactivity records. This skill guides focused ChEMBL queries, structure searches, and result interpretation.

Research & Learning View

packmol

Build Packmol Molecular Systems

by Chenghao-Wu

Preparing molecular dynamics starting structures requires precise Packmol syntax and geometry choices. This skill helps create inputs, solvation setups, interfaces, and validation steps for Packmol workflows.

Research & Learning View

medchem

Filter and Prioritize Medicinal Chemistry Libraries

by davila7

Large compound libraries are difficult to assess consistently with multiple medicinal chemistry criteria. This skill combines established filters, alerts, constraints, and reports.

Research & Learning View

deepchem

Build Molecular ML Workflows with DeepChem

by davila7

Molecular machine learning requires specialized data handling, featurization, splitting, and model selection. This skill provides DeepChem guidance, reference workflows, and runnable training scripts.

Research & Learning View

rdkit

Analyze Molecules with RDKit

by davila7

Advanced molecular workflows require careful control over parsing, descriptors, fingerprints, and structure queries. This skill provides focused RDKit guidance, references, and reusable scripts.

Research & Learning View

datamol

Analyze Molecular Data with Datamol

by davila7

Cheminformatics workflows often require detailed RDKit code for routine molecular processing. This skill provides focused Datamol guidance for analysis, visualization, and scalable data preparation.

Data & Analytics View