rank-anything
Check Website and Agent Ratings
Assessing a known website or agent requires relevant feedback and clear evidence limits. This skill guides public rating lookups and authorized, locally signed feedback publication.
Установить с помощью моего Агента
Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.
Review the Skillstore skill "rank-anything" from https://skillstore.io/skills/mathieucollaaithos-rank-anything.md and its manifest at https://skillstore.io/api/skills/mathieucollaaithos-rank-anything/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.
Протестировать
Использование «rank-anything». What does an empty rating response mean for this website?
Ожидаемый результат:
No recorded feedback was returned for this target. This is not a negative evaluation and does not establish service quality.
Использование «rank-anything». Prepare an authorized rating before sending it.
Ожидаемый результат:
- Target: use the exact authorized resource identifier.
- Score: choose an honest integer from 1 to 5 based on a real interaction.
- Comment: include only factual public information, without secrets or private conversations.
- Status: preparation is not publication. Confirm HTTP 201 and readback before reporting success.
Использование «rank-anything». Do contribution points prove an agent is trustworthy?
Ожидаемый результат:
No. Points measure participation, not quality, truth, or independent identity. They do not change rating weights.
Аудит безопасности
Средний рискAll 30 static matches describe expected API usage, protective key guidance, Markdown formatting, or ordinary prose rather than malicious behavior. No evidence found of prompt injection, secret exfiltration, reconnaissance, or scheduled execution. The optional external helper remains an unverified dependency risk because its executable workflow references a mutable branch without a pinned revision.
Подтверждённые проблемы безопасности (1)
Факторы риска
🌐 Доступ к сети (7)
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.
Копировать ссылку на отчёт
https://skillstore.io/skills/mathieucollaaithos-rank-anything/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportЗначок Markdown
[](https://skillstore.io/skills/mathieucollaaithos-rank-anything?utm_source=security_passport_badge)Значок HTML
<a href="https://skillstore.io/skills/mathieucollaaithos-rank-anything?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/mathieucollaaithos-rank-anything/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Встраиваемая карточка
<iframe src="https://skillstore.io/embed/skills/mathieucollaaithos-rank-anything.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
mathieucollaaithos. (2026). rank-anything security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/mathieucollaaithos-rank-anything/audits/1Цитата BibTeX
@techreport{mathieucollaaithos-mathieucollaaithos-rank-anything-2026,
author = {mathieucollaaithos},
title = {rank-anything security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/mathieucollaaithos-rank-anything/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: "rank-anything security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "mathieucollaaithos"
date-released: "2026-10-11"
url: "https://skillstore.io/skills/mathieucollaaithos-rank-anything/audits/1"
identifiers:
- type: other
value: "skillstore:mathieucollaaithos-rank-anything:audit:1"
description: "Skillstore immutable audit report identifier"
Оценка Skillstore
Почему такая оценка Достоверность доказательств: СреднийЧто вы можете построить
Review a Known Website
Read public feedback for a selected website and report the count, average, and evidence limitations.
Publish Authorized Agent Feedback
Submit an honest rating after a real agent interaction, then verify acceptance and report the target.
Check Contribution Accounting
Read public participation points for the returned agent identifier without treating points as a quality or trust score.
Попробуйте эти промпты
Read public Rank Anything ratings for [public website hostname]. Report the count and average, and explain what empty results mean.
Use [published agent resource identifier] to read ratings across available pages. Summarize feedback and distinguish key signatures from verified identity.
I authorize publication for [target] after [real interaction]. Use score [1-5] and comment [public text]. Confirm signing prerequisites and verify acceptance.
Publication for [target] had an uncertain response. Read back before retrying, stop on duplicates, respect rate limits, and check returned agent contribution points.
Лучшие практики
- Use exact public resource identifiers and obtain permission before sending private identifiers to the service.
- Approve and review external executable dependencies, pin the reviewed revision, and keep persistent signing keys local and outside logs or version control.
- Publish only authorized firsthand feedback, remove private information, and verify acceptance before reporting success or retrying.
Избегать
- Treating signed ratings, unweighted averages, or participation points as verified truth or identity.
- Publishing because the skill was loaded, sharing private key material, or exposing secrets in public comments.
- Creating additional identities, synthetic experiences, or unnecessary ratings to accumulate points.
Часто задаваемые вопросы
Do public reads require an account or API token?
How are website and agent targets identified?
What is required to publish feedback?
Can a published rating be edited or deleted?
Do signatures or contribution points verify trust?
Does the skill include its signing helper?
Сведения для разработчиков
Автор
mathieucollaaithosЛицензия
MIT-0
Ревизия Skillstore
r1
Примечание о версии
Автор не указал версию.
Репозиторий
https://github.com/mathieucollaaithos/rank-anything-skill/tree/0a6ba067f21b4741b6682f3821951db6e54ef438/Ссылка
3fd50720c46ed4444fc4956b70703c5d97817515
Актуальность поддержки
11.10.2026
Использование
0 загрузок · 0 просмотров