📦

heatstroke

Name: heatstroke
Author: tahodev

Révision du contenu r1 Risque moyen 🌐 Accès réseau📁 Accès au système de fichiers⚙️ Commandes externes

Check Japan Heat Risk with WBGT Data

Heat-risk planning requires location-specific readings with clear timestamps. This skill retrieves Japanese government WBGT forecasts and observations, matches stations, and presents five risk categories.

Prend en charge: Claude Codex Code(CC)

📊 68 Adéquat

Maintain this Skill? Claim it 📊 68 Adéquat

Installer avec mon Agent

Copiez cette demande dans votre Agent. Elle contient la page Skill de référence et le manifeste.

Demande d’agent

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

Votre Agent doit toujours présenter son plan et demander toute confirmation exigée par la politique de sécurité.

Ressources lisibles par les agents

Utilisez ces liens lorsqu’un Agent IA, un crawler ou un script a besoin d’un contexte propre au lieu de lire toute la page.

Détail Markdown GET /skills/tahodev-heatstroke.md manifest signé GET /api/skills/tahodev-heatstroke/manifest lockfile signé GET /api/skills/tahodev-heatstroke/lockfile

Tester

Utilisation de « heatstroke ». Explain the documented Tokyo forecast example.

Résultat attendu:

Documented historical example: Tokyo, station 44132.
Announcement: 2026-09-25 17:00 JST. Forecast time: 2026-09-25 18:00 JST.
WBGT: 21.0 degrees Celsius after dividing the source value by ten. Category: caution.
This historical example does not describe current conditions.

Utilisation de « heatstroke ». Interpret the documented Tokyo observation example.

Résultat attendu:

Documented historical example: Tokyo, 2026-09-01 00:00 JST.
Outdoor WBGT: 21.9 degrees Celsius. Category: caution.
One observation cannot establish the daily maximum or current heat risk.

Audit de sécurité

Risque moyen

v1 • 13/10/2026 Ouvrir le rapport versionné

All 70 static findings are false positives involving public API access, documented cache storage, Markdown syntax, or readable Japanese text. No evidence found of prompt injection, credential access, or unauthorized data exfiltration. Two semantic findings identify host-timezone errors and misleading safe classifications when observations contain no valid values.

Fichiers analysés

327

Lignes analysées

Éléments à examiner

Faux positifs ignorés

Préoccupations de sécurité confirmées (2)

Moyen

lookup.py:70-77 lookup.py:94-98 lookup.py:107-111 SKILL.md:106

Host Timezone Can Select Stale Heat Forecasts

Default forecast announcements and survey dates use naive host-local timestamps, although the API expects JST. Non-JST hosts can retrieve older forecasts or the wrong observation date, misleading heat-risk decisions.

The helper uses datetime.now() without timezone conversion. A local check selected the previous day's 17:00 announcement at 03:30 UTC, instead of the current day's 11:00 JST announcement.

Moyen

lookup.py:116-125 lookup.py:25-30

Missing Observations Produce a Misleading Safe Maximum

The survey maximum starts at zero and remains zero when every outdoor reading is missing or nonnumeric. The summary then labels the day safe despite having no valid observations, potentially encouraging unsafe heat exposure.

A mocked survey containing an empty outdoor reading produced a 0.0 maximum with the safe category. The code does not track whether any valid observations exist.

Facteurs de risque

🌐 Accès réseau (15)

lookup.py:20 lookup.py:36 lookup.py:81 lookup.py:12 lookup.py:21 lookup.py:22 lookup.py:14 SKILL.md:20 SKILL.md:21 SKILL.md:22 SKILL.md:23 SKILL.md:27 SKILL.md:32 SKILL.md:42 SKILL.md:60

📁 Accès au système de fichiers (9)

lookup.py:9 lookup.py:16 lookup.py:9 lookup.py:16 lookup.py:36 lookup.py:33 SKILL.md:82 SKILL.md:100 SKILL.md:100

⚙️ Commandes externes (30)

Audité par: codex

Partager et citer ce rapport

Partagez le rapport d’évaluation versionné, le badge neutre, la carte intégrable et les citations. Skillstore présente les preuves sans décider si ce Skill est sûr.

Ouvrir le rapport versionné

Copier le lien du rapport

https://skillstore.io/skills/tahodev-heatstroke/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Badge Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/tahodev-heatstroke/security.svg)](https://skillstore.io/skills/tahodev-heatstroke?utm_source=security_passport_badge)

Badge HTML

<a href="https://skillstore.io/skills/tahodev-heatstroke?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tahodev-heatstroke/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Carte intégrable

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

Citations académiques (APA · BibTeX · CFF)

Citation APA

tahodev. (2026). heatstroke security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/tahodev-heatstroke/audits/1

Citation BibTeX

@techreport{tahodev-tahodev-heatstroke-2026,
  author = {tahodev},
  title = {heatstroke security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/tahodev-heatstroke/audits/1},
  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: "heatstroke security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "tahodev"
date-released: "2026-10-13"
url: "https://skillstore.io/skills/tahodev-heatstroke/audits/1"
identifiers:
  - type: other
    value: "skillstore:tahodev-heatstroke:audit:1"
    description: "Skillstore immutable audit report identifier"

Score Skillstore

Pourquoi ce score Niveau de confiance des preuves: Moyen

Architecture

Maintenabilité

Contenu

Communauté

Conformité aux spécifications

Ce que vous pouvez créer

Review Event Heat Conditions

Retrieve a nearby station forecast before an outdoor event and review timestamps alongside official activity guidance.

Inspect Workplace Heat Observations

Review a selected station's daily outdoor WBGT readings and risk categories without treating regional data as an onsite measurement.

Research Local Heat Patterns

Find station identifiers and retrieve dated forecasts or observations for comparisons using the documented public API.

Essayez ces prompts

Find a Station

Find stations with names containing Tokyo. Show their identifiers and whether measured observations are available. Use the Japanese station name if needed.

Review a Station Forecast

Retrieve the next 24 hours of WBGT forecasts for station 44132. Include JST announcement and forecast times, converted values, and risk categories.

Inspect Daily Observations

Retrieve station 44132 observations for 2026-09-01. Show hourly outdoor readings and risk categories. Report a daily maximum only when valid readings exist.

Validate a Nearby Forecast

Find the nearest station to latitude 35.68, longitude 139.69. Verify the latest JST announcement explicitly and summarize forecast risk, distance, and data limitations.

Bonnes pratiques

Include station identity, observation or forecast time, and JST announcement time in every result.
Validate API status and available readings; distinguish missing data from low heat risk.
Confirm JST dates explicitly on non-JST hosts and consult official activity guidance before making safety decisions.

Éviter

Presenting historical forecasts or empty responses as current conditions.
Treating a missing-data zero maximum as proof that outdoor activity is safe.
Using JIS prefecture codes as API prefecture identifiers instead of resolving station numbers.

Foire aux questions

Do I need an API key or account?

No. The documented Japanese government WBGT API provides public data without an API key, login, or registration.

Which locations are covered?

The documented station master contains 865 locations across Japan. Search station names or supply coordinates to choose a nearby station.

How frequently are forecasts published?

The skill documents announcements at 05:00, 11:00, and 17:00 JST, with forecast values in three-hour intervals.

Where does the helper store data?

It caches station metadata in ~/.cache/kurashi-skill/heatstroke/. The refresh option downloads a new station master; forecasts and observations require API requests.

What does an empty response mean?

Data may be unavailable outside the service season, delayed, or requested for an incorrect announcement time. Empty results do not indicate safe conditions.

Can this determine whether exercise is safe?

No. WBGT is a general heat-risk indicator, not individual medical advice. Consult official activity guidance and verify valid readings and timestamps.