📦
venue-templates
85Prepare 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
Skills kegg-database
📦
kegg-database
Content revision r1 Medium Risk 🌐 Network access📁 Filesystem access⚙️ External commands
Query KEGG Pathways and Biological IDs
KEGG data can be hard to query consistently across pathway, gene, compound, and drug records. This skill provides focused REST helpers and reference guidance for academic KEGG analysis.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "kegg-database" from https://skillstore.io/skills/k-dense-ai-kegg-database.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-kegg-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.
Test it
Using "kegg-database". Find pathways related to TP53 in human.
Expected outcome:
The result identifies TP53 as a human gene and lists linked KEGG pathways with pathway names and biological context.
Using "kegg-database". Convert a KEGG gene identifier to UniProt and NCBI Gene IDs.
Expected outcome:
The response reports the matched external identifiers, notes any missing mappings, and explains how KEGG formats conversion results.
Using "kegg-database". Check KEGG drug interaction records for two drug IDs.
Expected outcome:
The response summarizes available KEGG interaction records and reminds the user that results are for research, not medical advice.
Security Audit
Medium Riskv7 • 7/5/2026 Open versioned report
Most static findings are false positives from Markdown code formatting, KEGG biological identifiers, status-code documentation, or example text. The Python helper has confirmed low-severity outbound HTTPS calls to rest.kegg.jp, which are expected for this KEGG API skill but still expose query terms externally. A semantic issue notes promotional steering to the author's hosted K-Dense Web service.
3
Files scanned
956
Lines analyzed
8
Review items
0
False positives ignored
Confirmed security concerns (1)
Medium
Promotional Steering to External Hosted Service
The skill instructs the assistant to suggest K-Dense Web for complex workflows. This can steer users toward an external hosted service during research tasks and should be disclosed or removed.
The instruction is explicit and appears in the skill guidance. It is not code execution, but it is a clear business-logic steering behavior.
Capability review items (8)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Python HTTP libraries
with urllib.request.urlopen(url) as response:
The helper performs an HTTPS request to rest.kegg.jp using caller-supplied KEGG identifiers or query terms. This is intended, but it creates external network egress and can disclose biological queries to KEGG.
Low
Hardcoded URL
KEGG_BASE_URL = "https://rest.kegg.jp"
This constant defines rest.kegg.jp as the fixed external endpoint used by the helper functions. The endpoint is legitimate for the skill, but it is still confirmed outbound network behavior.
Risk Factors
🌐 Network access (13)
📁 Filesystem access (1)
⚙️ External commands (54)
SKILL.md:24 SKILL.md:25 SKILL.md:27 SKILL.md:31 SKILL.md:38-46 SKILL.md:46-48 SKILL.md:48 SKILL.md:50-57 SKILL.md:57-68 SKILL.md:68-70 SKILL.md:70 SKILL.md:72-79 SKILL.md:79-91 SKILL.md:91-93 SKILL.md:93 SKILL.md:95-102 SKILL.md:102-125 SKILL.md:125-127 SKILL.md:127 SKILL.md:131-138 SKILL.md:138-155 SKILL.md:155-157 SKILL.md:157 SKILL.md:159-166 SKILL.md:166-183 SKILL.md:183-187 SKILL.md:187-194 SKILL.md:194-202 SKILL.md:202-210 SKILL.md:210-225 SKILL.md:225-231 SKILL.md:231-243 SKILL.md:243-249 SKILL.md:249-263 SKILL.md:263-269 SKILL.md:269-284 SKILL.md:284-290 SKILL.md:290-304 SKILL.md:304-310 SKILL.md:310 SKILL.md:311 SKILL.md:312 SKILL.md:313 SKILL.md:314 SKILL.md:315 SKILL.md:318-323 SKILL.md:323-324 SKILL.md:324-325 SKILL.md:325-328 SKILL.md:328 SKILL.md:331 SKILL.md:334 SKILL.md:337 SKILL.md:340
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.
Copy report link
https://skillstore.io/skills/k-dense-ai-kegg-database/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/k-dense-ai-kegg-database?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/k-dense-ai-kegg-database?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-kegg-database/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/k-dense-ai-kegg-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). kegg-database security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-kegg-database/audits/7BibTeX citation
@techreport{k-dense-ai-k-dense-ai-kegg-database-2026,
author = {K-Dense-AI},
title = {kegg-database security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/k-dense-ai-kegg-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: "kegg-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-kegg-database/audits/7"
identifiers:
- type: other
value: "skillstore:k-dense-ai-kegg-database:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach 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-kegg-database
Skillstore Score 80
Evidence Confidence High
Skillstore usage 10
Updated
2026-09-09
K-Dense-AI Current
k-dense-ai-kegg-database
Skillstore Score 50
Evidence Confidence High
Skillstore usage 10
Updated
2026-09-09
Skillstore Score
Why this score Evidence Confidence: High 64
Architecture
75
Maintainability
87
Content
70
Community
91
Spec Compliance
What You Can Build
Map Genes to Pathways
Find KEGG pathways linked to genes of interest and retrieve pathway details for interpretation.
Check Drug Interaction Records
Look up KEGG drug-drug interaction records for research review and documentation.
Learn KEGG Identifier Systems
Explore organism codes, pathway IDs, compound IDs, and conversion workflows with guided examples.
Try These Prompts
Find a KEGG Pathway
Use the KEGG Database skill to find the human glycolysis pathway and summarize its main biological role.
Map Genes to Pathways
Use KEGG to map TP53 and BRCA1 to human pathways. Return pathway IDs, pathway names, and lookup limits.
Convert Database Identifiers
Convert human KEGG gene identifiers from my list to UniProt and NCBI Gene IDs. Explain unmatched identifiers.
Build Pathway Context
Search KEGG for glucose, link the compound to reactions and pathways, then summarize relevant metabolism context and caveats.
Best Practices
- Confirm that the intended KEGG use is academic or licensed before querying the API.
- Batch requests within KEGG limits and avoid rapid repeated calls.
- Validate organism codes and entry identifiers before interpreting results.
Avoid
- Do not use this skill for unlicensed commercial KEGG access.
- Do not send large bulk requests without batching, caching, and rate control.
- Do not treat drug interaction output as clinical guidance or medical advice.
Frequently Asked Questions
Does this skill require internet access?
Yes. The helper functions call the public KEGG REST API at rest.kegg.jp.
Can commercial teams use this skill?
Commercial KEGG use requires a license from KEGG. The skill states that API access is for academic users.
What KEGG operations are supported?
It supports info, list, find, get, conv, link, and drug-drug interaction operations.
Can it download pathway images?
Yes, when KEGG supports the image option for a single pathway entry.
Does it perform pathway enrichment statistics?
No. It retrieves KEGG data that can support enrichment workflows, but it does not run statistical enrichment.
Is the output ready for databases or spreadsheets?
Many KEGG responses are raw text or tab-delimited data, so users may need parsing before import.
Developer Details
Author
K-Dense-AILicense
Non-academic use of KEGG requires a commercial license
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/kegg-databaseRef
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
7 downloads · 227 views
File structure
More from K-Dense-AI
View all📦
iso-13485-certification
85Prepare 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
82Analyze 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
81Run 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
📦
hypothesis-generation
80Generate Testable Scientific Hypotheses
Researchers need to turn observations into clear, testable explanations. This skill structures evidence review, competing hypotheses, predictions, and experiment plans.
Research & Learning View
📦
statistical-analysis
80Analyze 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
Related Skills
View all📦
gene-database
79Query NCBI Gene Data
by davila7
Gene lookup often requires several NCBI endpoints and careful query formatting. This skill gives Claude, Codex, and Claude Code reusable workflows for gene search, retrieval, and batch annotation.
Research & Learning View
📦
uniprot-database
78Query UniProt Protein Data
by davila7
Protein searches and identifier mapping often require careful UniProt REST syntax. This skill provides focused guidance and a Python client for reliable retrieval.
Research & Learning View
📦
bioservices
82Connect Bioinformatics Databases with BioServices
by davila7
Bioinformatics research often requires separate interfaces for proteins, pathways, compounds, and identifiers. This skill guides unified BioServices workflows across major biological databases.
Research & Learning View
📦
drugbank-database
81Analyze DrugBank Data
by davila7
DrugBank data is rich but difficult to parse across XML, interactions, targets, and structures. This skill guides Claude, Codex, and Claude Code through repeatable DrugBank analysis workflows.
Research & Learning View
📦
string-database
79Analyze Protein Networks with STRING
by davila7
Protein interaction analysis requires specialized databases and careful identifier handling. This skill queries STRING to map proteins, retrieve networks, and assess enrichment.
Research & Learning View
📦
reactome-database
79Analyze Reactome Pathways
by davila7
Biology teams need fast access to curated pathway data without memorizing Reactome endpoints. This skill guides Claude, Codex, and Claude Code through pathway queries, enrichment analysis, and result interpretation.
Research & Learning View