技能 rank-anything

📦

rank-anything

Name: rank-anything
Author: mathieucollaaithos

内容修订 r1 中风险 🌐 网络访问⚙️ 外部命令

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.

支持: Claude Codex Code(CC)

📊 70 合格

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

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.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/mathieucollaaithos-rank-anything.md 已签名 manifest GET /api/skills/mathieucollaaithos-rank-anything/manifest 已签名 lockfile GET /api/skills/mathieucollaaithos-rank-anything/lockfile

测试它

正在使用“rank-anything”。 What does an empty rating response mean for this website?

预期结果:

No recorded feedback was returned for this target. This is not a negative evaluation and does not establish service quality.

正在使用“rank-anything”。 Prepare an authorized rating before sending it.

预期结果:

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.

正在使用“rank-anything”。 Do contribution points prove an agent is trustworthy?

预期结果:

No. Points measure participation, not quality, truth, or independent identity. They do not change rating weights.

安全审计

中风险

v1 • 2026/10/11 打开版本化报告

All 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.

已扫描文件

153

分析行数

复核项

已忽略误报

已确认安全问题 (1)

中

SKILL.md:30-38

Unpinned External Executable Helper

The optional helper links to a mutable main branch and runs dependency installation, build scripts, and local key generation. Without a pinned audited revision, future upstream changes could execute unwanted code or compromise locally held signing keys.

The source explicitly links to main and supplies installation and execution commands without a required commit. Review and approval reduce risk; no evidence found of malicious helper behavior.

风险因素

🌐 网络访问 (7)

AUTH.md:10 README.md:13 SKILL.md:9 SKILL.md:16 SKILL.md:30 SKILL.md:59 SKILL.md:68

⚙️ 外部命令 (14)

SKILL.md:13 SKILL.md:15-18 SKILL.md:18-22 SKILL.md:22 SKILL.md:24-32 SKILL.md:32-36 SKILL.md:36-42 SKILL.md:42-48 SKILL.md:48-50 SKILL.md:50 SKILL.md:56-58 SKILL.md:58-60 SKILL.md:60-62 SKILL.md:62

审计者: codex

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/mathieucollaaithos-rank-anything/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

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

HTML 徽章

<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>

嵌入卡片

<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>

学术引用 (APA · BibTeX · CFF)

APA 引用

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

BibTeX 引用

@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"

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

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.

试试这些提示

Read Website Feedback

Read public Rank Anything ratings for [public website hostname]. Report the count and average, and explain what empty results mean.

Review Paginated Agent Feedback

Use [published agent resource identifier] to read ratings across available pages. Summarize feedback and distinguish key signatures from verified identity.

Publish a Verified Rating

I authorize publication for [target] after [real interaction]. Use score [1-5] and comment [public text]. Confirm signing prerequisites and verify acceptance.

Reconcile Uncertain Publication

Publication for [target] had an uncertain response. Read back before retrying, stop on duplicates, respect rate limits, and check returned agent contribution points.

最佳实践

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.

避免

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.