Навыки dbs-content-risk-check

📦

dbs-content-risk-check

Name: dbs-content-risk-check
Author: dontbesilent2025

Ревизия содержимого r1 Безопасно ⚙️ Внешние команды

Check Publication Risks Before Posting

Creators need to distinguish automated moderation signals from substantive publication problems. This skill identifies specific concerns and suggests minimal edits while preserving personal expression.

Поддерживает: Claude Codex Code(CC)

🥉 77 Бронза

Maintain this Skill? Claim it 🥉 77 Бронза

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента

Review the Skillstore skill "dbs-content-risk-check" from https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check.md and its manifest at https://skillstore.io/api/skills/dontbesilent2025-dbs-content-risk-check/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Markdown-детали GET /skills/dontbesilent2025-dbs-content-risk-check.md Подписанный manifest GET /api/skills/dontbesilent2025-dbs-content-risk-check/manifest Подписанный lockfile GET /api/skills/dontbesilent2025-dbs-content-risk-check/lockfile

Протестировать

Использование «dbs-content-risk-check». Review a promotional caption: This ordinary tea cures diabetes in seven days. No supporting evidence is supplied.

Ожидаемый результат:

Possible machine trigger: the caption combines product promotion with an explicit disease-treatment claim.
Substantive concern: the caption promises a cure for diabetes without supporting evidence or an authorized medical indication.
Minimal change: remove the cure and timing claims. Use only verified product facts within the permitted scope.
Review boundary: images, account details, and comments were not supplied.

Использование «dbs-content-risk-check». Review a personal study video script and suggest three overlay lines. The author describes one week of personal practice without promising results.

Ожидаемый результат:

No substantive problem is apparent in the supplied description. Personal experience can remain.
Requested overlay text:
Personal study experience
Results are not guaranteed
Adapt to your circumstances
Review boundary: the footage and audio were not supplied.

Аудит безопасности

Безопасно

v1 • 17.10.2026 Открыть версионный отчет

All 11 static findings are false positives: Markdown backticks are not shell execution, and readable Chinese text explains the entropy alerts. No evidence found of concealed payloads, credential theft, unauthorized data transfers, or prompt injection. The skill limits link access and permits relevant official policy lookups.

Просканировано файлов

342

Проанализировано строк

Пункты проверки

Ложные срабатывания проигнорированы

Факторы риска

⚙️ Внешние команды (8)

SKILL.md:191 SKILL.md:257-261 SKILL.md:261-265 SKILL.md:265-269 SKILL.md:269-285 SKILL.md:285-308 SKILL.md:308-336 SKILL.md:336

Последний завершенный статический и семантический аудит не обнаружил подтвержденных проблем безопасности. Это не доказывает отсутствие побочных эффектов у навыка.

Аудитор:: codex

Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет

Копировать ссылку на отчёт

https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/dontbesilent2025-dbs-content-risk-check/security.svg)](https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dontbesilent2025-dbs-content-risk-check/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/dontbesilent2025-dbs-content-risk-check.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Академические ссылки (APA · BibTeX · CFF)

Цитата APA

dontbesilent2025. (2026). dbs-content-risk-check security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check/audits/1

Цитата BibTeX

@techreport{dontbesilent2025-dontbesilent2025-dbs-content-risk-check-2026,
  author = {dontbesilent2025},
  title = {dbs-content-risk-check security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check/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: "dbs-content-risk-check security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "dontbesilent2025"
date-released: "2026-10-17"
url: "https://skillstore.io/skills/dontbesilent2025-dbs-content-risk-check/audits/1"
identifiers:
  - type: other
    value: "skillstore:dontbesilent2025-dbs-content-risk-check:audit:1"
    description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний

Архитектура

Сопровождаемость

Контент

Сообщество

Соответствие спецификации

Что вы можете построить

Review a Social Post

Locate potential problems in a caption and distinguish machine triggers from actual misleading or harmful statements.

Check Promotional Claims

Review product claims, commercial relationships, supporting evidence, and contact routes before publishing sponsored content.

Clarify Video Context

Check a supplied script and accessible footage, then draft truthful overlay text when personal experiences could be mistaken for guarantees.

Попробуйте эти промпты

Review a Draft

Check this draft for publication risks on [platform]: [draft]. Separate possible machine triggers from substantive problems and suggest only necessary local edits.

Check Commercial Content

Review this promotional post for [platform]: [post]. Product category: [category]. Commercial relationship: [relationship]. Available evidence: [evidence]. Identify missing disclosures and unsupported claims.

Review Video Materials

Review these video materials for [platform]: [materials]. Identify unchecked surfaces and necessary edits. Add truthful three-line overlay wording only if context requires it.

Verify Policy-Dependent Concerns

Audit this campaign for [platform]: [materials]. Check policy-dependent concerns against current official sources. Cite rule titles, dates, applicability, and links. State unresolved facts.

Лучшие практики

Provide the target platform, intended audience, commercial relationships, and available supporting evidence.
Supply the actual publication surfaces and distinguish original visuals from OCR transcripts.
Verify policy-dependent recommendations against current official rules and resolve missing qualifications before publishing.

Избегать

Treating a flagged keyword or machine signal as proof of a substantive violation.
Using disclaimers to preserve false claims, missing qualifications, undisclosed advertising, or privacy exposure.
Requesting altered spellings, hidden contact details, or coded comments to evade moderation.

Часто задаваемые вопросы

Does this skill guarantee that a platform will approve my post?

No. It identifies visible concerns and uncertainty but cannot predict or guarantee platform decisions.

What materials can I submit?

Submit drafts, captions, OCR text, scripts, comments, profiles, images, or accessible video materials. Visual and audio inspection depends on the host tool.

Will it rewrite my entire draft?

Not by default. It recommends local changes and preserves personal style unless you request a full rewrite.

When does it produce video overlay text?

When requested or when truthful context boundaries are needed. Overlay text cannot replace corrections, evidence, disclosures, or qualifications.

Does it automatically open links in my draft?

No. Draft links are reviewed as content by default. Explicit webpage review can expand scope, and policy-dependent questions may require official-source lookups.

Can it verify current platform rules?

When official sources are accessible, it checks relevant current rules. Without official evidence, it must state the uncertainty rather than invent enforcement details.