Compétences feeling-search
📦

feeling-search

v1.1.0 Révision du contenu r3 Risque moyen ⚙️ Commandes externes🌐 Accès réseau📁 Accès au système de fichiers🔑 Variables d’environnement

Find Visual Styles from Mood Descriptions

Vague mood descriptions make visual direction difficult to communicate. Feeling Search uses a cached lexicon to suggest named styles and matching vocabulary, with optional paid cloud analysis.

Prend en charge: Claude Codex Code(CC)
Maintain this Skill? Claim it ⚠️ 50 Médiocre

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 "feeling-search" from https://skillstore.io/skills/xixi048-feeling-search.md and its manifest at https://skillstore.io/api/skills/xixi048-feeling-search/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.

Tester

Utilisation de « feeling-search ». Match the mood: walking alone past a convenience store in the rain under cold white light.

Résultat attendu:

  • Documented local example, translated from Chinese: matched words include light and white.
  • Listed candidates include Delft School at 0.25 and De Stijl at 0.22.
  • These are dictionary ranking scores, not confidence probabilities or guaranteed artistic matches.

Utilisation de « feeling-search ». Explain the word cold light using the free lookup endpoint.

Résultat attendu:

  • API documentation example: cold light means even illumination with a high color temperature.
  • The example associates this term with Luminism and reports its use across 17 styles.
  • Related vocabulary includes cool white and fluorescent light; confusing opposite terms require care.

Utilisation de « feeling-search ». Analyze a description with no local matches, without approving cloud analysis.

Résultat attendu:

  • Source: local. No dictionary words matched.
  • Paid cloud analysis was not called because cloud permission was not enabled.
  • Try free fuzzy matching before considering a paid request.

Audit de sécurité

Risque moyen

Most static alerts are false positives from Markdown backticks, multilingual documentation, normal cache operations, and documented API access. Quota tokens lack explicit restrictive file permissions, appear in request URLs, and lack transport origin protections. No evidence found of malicious exfiltration intent, prompt injection, hidden command execution, or code obfuscation.

3
Fichiers analysés
1,066
Lignes analysées
1
Éléments à examiner
0
Faux positifs ignorés

Préoccupations de sécurité confirmées (2)

Moyen
Quota Credentials Exposed in Request URLs
Quota setup and balance checks put the bearer token in the URL query. Reverse proxies and access logs can retain this spendable credential.
Both quota request paths concatenate the token into the URL. The API contract supports header authentication, so URL exposure is avoidable.
Moyen
Quota Credentials Lack HTTPS Origin Protection
FS_API_BASE accepts HTTP, and default urllib redirects can forward X-FS-Quota headers across origins. Misconfigured endpoints or unsafe redirects can expose quota credentials.
Endpoint configuration has no scheme validation, and both transports use urllib defaults without redirect restrictions. Exploitation requires unsafe configuration or a cross-origin redirect.
Éléments d’évaluation des capacités (1)

Il s’agit de capacités locales réelles qui peuvent être attendues pour cette compétence ; elles nécessitent donc un examen, mais ne sont pas comptabilisées comme comportement malveillant confirmé.

Moyen
Python file write/append
with open(tmp, "w", encoding="utf-8") as fh:
Quota tokens are written in plaintext without restrictive permissions; common umasks create files readable by other local users.
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
Évaluation de sécurité

Copier le lien du rapport

https://skillstore.io/skills/xixi048-feeling-search/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Badge Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/xixi048-feeling-search/security.svg)](https://skillstore.io/skills/xixi048-feeling-search?utm_source=security_passport_badge)

Badge HTML

<a href="https://skillstore.io/skills/xixi048-feeling-search?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/xixi048-feeling-search/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Carte intégrable

<iframe src="https://skillstore.io/embed/skills/xixi048-feeling-search.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

xixi048. (2026). feeling-search security audit report (audit version 3) [Author version 1.1.0]. Skillstore. https://skillstore.io/skills/xixi048-feeling-search/audits/3

Citation BibTeX

@techreport{xixi048-xixi048-feeling-search-2026, author = {xixi048}, title = {feeling-search security audit report (audit version 3)}, institution = {Skillstore}, year = {2026}, number = {3}, url = {https://skillstore.io/skills/xixi048-feeling-search/audits/3}, note = {Author version 1.1.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "feeling-search security audit report (audit version 3)" version: "1.1.0" type: report authors: - name: "xixi048" date-released: "2026-10-27" url: "https://skillstore.io/skills/xixi048-feeling-search/audits/3" identifiers: - type: other value: "skillstore:xixi048-feeling-search:audit:3" description: "Skillstore immutable audit report identifier"

Score Skillstore

Pourquoi ce score Niveau de confiance des preuves: Moyen
64
Architecture
100
Maintenabilité
87
Contenu
65
Communauté
91
Conformité aux spécifications

Ce que vous pouvez créer

Translate Creative Briefs

Convert a client mood description into candidate visual styles and matched vocabulary for a design discussion.

Develop Environment Art Direction

Compare styles for a game location and inspect each candidate through definitions, matched terms, and optional paid references.

Prepare Image Prompt Vocabulary

Find style names and distinguishing terms for prompts used in a separate image generation tool.

Essayez ces prompts

Find Initial Style Candidates
Find visual styles for this mood: [description]. Use free local matching and report style names, definitions, and matched words.
Improve Sparse Local Matches
Analyze [description] locally, then retry with fuzzy matching if results are sparse. Compare both results without using paid cloud analysis.
Compare Style Vocabulary
Compare [style A] and [style B] using their vocabulary and free word lookups. Highlight distinguishing terms and explain overlaps.
Retrieve Approved Paid References
Use one paid image request for these styles: [up to five IDs]. Report image type, attribution, and source links; exclude placeholders.

Bonnes pratiques

  • Use free local matching first, and approve any paid cloud or image request explicitly.
  • Keep descriptions concise, inspect matched words, and treat ranking scores as suggestions rather than artistic certainty.
  • Protect quota credentials, retain image attribution, and exclude placeholder images from visual references.

Éviter

  • Uploading confidential creative briefs through cloud analysis or remote lookups without permission.
  • Treating dictionary matches as complete semantic interpretation or a guaranteed correct art direction.
  • Assuming reference images are generated artwork or that commercial reuse rights are automatically verified.

Foire aux questions

Does Feeling Search generate images?
No. It suggests visual styles and vocabulary, and can request reference image metadata from the service.
Which operations are free?
Local matching, dictionary downloads, word lookups, style vocabulary, status checks, and quota balance checks are documented as free.
When does analysis use the paid cloud endpoint?
Only when local word matches are zero, cloud permission is enabled, and a quota token is available. Reference retrieval is separately paid.
Can I use it without an internet connection?
Local analysis works with a valid downloaded dictionary and offline mode. Expired caches currently fail offline, and remote lookup commands cannot run offline.
What does installation require?
The client uses Python 3.8 or later and the standard library. A dictionary download is needed before local matching.
How should I protect quota credentials and reference rights?
Restrict credential file access and use trusted HTTPS endpoints. Check reference licenses and attribution before reuse; marketplace review does not verify image rights.

Détails du développeur

Auteur

xixi048

Licence

MIT

Version de l’auteur

v1.1.0

Révision Skillstore

r3

Réf

1e22a7c9000672c440acafc13dc0c17f8ae8d00a

Récence de maintenance

27/10/2026

Utilisation

0 téléchargements · 1 vues

Structure de fichiers

Autres compétences de xixi048

Tout afficher
Tout afficher