スキル socialdatax-content-research-assistant

📦

socialdatax-content-research-assistant

Name: socialdatax-content-research-assistant
Author: devinchen2014

コンテンツリビジョン r1 中リスク ⚙️ 外部コマンド🌐 ネットワークアクセス🔑 環境変数

Research Social Media Content with SocialDataX

Social media research requires collecting evidence from different platforms and separating facts from interpretation. This skill guides SocialDataX queries and organizes topics, comments, creator profiles, and engagement signals.

対応: Claude Codex Code(CC)

📊 64 十分

Maintain this Skill? Claim it 📊 64 十分

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト

Review the Skillstore skill "socialdatax-content-research-assistant" from https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant.md and its manifest at https://skillstore.io/api/skills/devinchen2014-socialdatax-content-research-assistant/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/devinchen2014-socialdatax-content-research-assistant.md 署名済み manifest GET /api/skills/devinchen2014-socialdatax-content-research-assistant/manifest 署名済み lockfile GET /api/skills/devinchen2014-socialdatax-content-research-assistant/lockfile

テストする

「socialdatax-content-research-assistant」を使用しています。 Illustrative request: compare content angles for home workouts across two platforms.

期待される結果:

Illustrative brief, not live findings.
XHS sample theme: small-space routines and equipment choices.
Douyin sample theme: short demonstrations and repeatable challenges.
Research angle: compare beginner routines, supported by source references from each platform.
Limit: sampled posts do not establish overall audience preferences.

「socialdatax-content-research-assistant」を使用しています。 Illustrative request: summarize feedback from a product review sample.

期待される結果:

Illustrative review summary, not live findings.
Observed themes: setup questions, size concerns, and requests for comparison examples.
Interpretation: a practical setup guide may address repeated questions.
Next step: inspect complete reply threads before assigning sentiment.
Coverage: report collected review counts and mark any incomplete pages.

セキュリティ監査

中リスク

v1 • 2026/11/2 バージョン別レポートを開く

Of 148 static findings, two confirm unpinned npm execution risks; 146 are Markdown, platform identifier, credential configuration, URL, or language heuristic false positives. A separate finding addresses unconditional disclosure of token-bearing XHS links. No evidence of malicious prompt injection or credential exfiltration was found in the supplied files; external package implementation was unavailable.

スキャンされたファイル

338

解析済み行数

レビュー項目

誤検知を無視

確認済みのセキュリティ上の懸念 (1)

中

SKILL.md:273

Unconditional Forwarding of Token-Bearing XHS Links

The instruction requires preserving xsec_token in note_url during final answers, storage, and forwarding, and explicitly forbids redaction. This can disclose link tokens outside the authorized research context; their privileges are not established by these files.

The text explicitly applies the no-redaction rule to forwarding and storage, without audience restrictions. Token sensitivity remains uncertain, so no account-access claim is made.

機能レビュー項目 (2)

これらは、このスキルに期待される可能性のある実際のローカル機能であるため、レビューが必要ですが、確認済みの悪意ある動作としてはカウントされません。

中

SKILL.md:31-139

Ruby/shell backtick execution

```bash

This fenced block directs agents to execute socialdatax-skills@latest through npx -y. Unpinned downloaded code can access local files and credentials; the risk is package execution, not Ruby backticks.

中

SKILL.md:143-217

Ruby/shell backtick execution

```bash

This second command block also executes socialdatax-skills@latest using npx -y. A mutable remote release runs with agent permissions without version pinning or integrity verification.

リスク要因

⚙️ 外部コマンド (50)

🌐 ネットワークアクセス (3)

SKILL.md:7 SKILL.md:25 SKILL.md:319

🔑 環境変数 (6)

SKILL.md:7 SKILL.md:25 SKILL.md:307 SKILL.md:318 SKILL.md:320 SKILL.md:327

監査者: codex

このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く

レポートリンクをコピー

https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/devinchen2014-socialdatax-content-research-assistant/security.svg)](https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/devinchen2014-socialdatax-content-research-assistant/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/devinchen2014-socialdatax-content-research-assistant.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学術引用 (APA · BibTeX · CFF)

APA形式の引用

devinchen2014. (2026). socialdatax-content-research-assistant security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant/audits/1

BibTeX形式の引用

@techreport{devinchen2014-devinchen2014-socialdatax-content-research-assistant-2026,
  author = {devinchen2014},
  title = {socialdatax-content-research-assistant security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant/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: "socialdatax-content-research-assistant security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "devinchen2014"
date-released: "2026-11-02"
url: "https://skillstore.io/skills/devinchen2014-socialdatax-content-research-assistant/audits/1"
identifiers:
  - type: other
    value: "skillstore:devinchen2014-socialdatax-content-research-assistant:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore スコア

このスコアの理由証拠の信頼度: 中

アーキテクチャ

保守性

コンテンツ

コミュニティ

仕様準拠

作成できるもの

Plan Evidence-Based Content Topics

Compare available hot-list signals and keyword samples, then identify content angles supported by platform-specific evidence.

Review Brand Feedback

Analyze comments and supported product reviews to summarize recurring needs, objections, and questions without treating samples as population estimates.

Compare Creator Positioning

Review candidate creator profiles and recent posts to compare topic focus, publishing patterns, and visible engagement signals.

これらのプロンプトを試す

Explore a Topic

Search XHS for [topic] using one page. Summarize recurring content angles and include returned source references.

Analyze Audience Comments

Review comments on [supported content link], stopping after 30 main comments. Separate observed themes from interpretation and mark incomplete reply threads.

Compare Creator Profiles

Compare these [platform] creator profiles: [profile links]. Use one content page each and separate profile facts, content evidence, and partnership questions.

Build a Cross-Platform Research Brief

Research [topic] on XHS, Douyin, and YouTube, with at most two pages per platform. Compare evidence, disclose sampling limits, and preserve partial results.

ベストプラクティス

Set platform, query, page limits, and item limits before collection, and confirm account balance.
Keep evidence separated by platform and distinguish retrieved facts from analytical judgments.
Use a reviewed CLI version, protect API keys, and review token-bearing links before sharing reports.

回避

Treating a small search sample or hot list as proof of a platform-wide trend.
Reusing pagination tokens across different queries, content items, or reply threads.
Publishing API keys or token-bearing links without reviewing access and disclosure risks.

よくある質問

What must I configure before using this skill?

Configure SOCIALDATAX_API_KEY and network access. Direct CLI execution also requires Node.js and npm, and API calls require sufficient SocialDataX balance.

Which platforms are covered?

Documented platforms include XHS, Douyin, Kuaishou, Bilibili, Zhihu, Instagram, X, YouTube, TikTok, Weibo, Toutiao, WeChat, and Haokan.

Does the skill publish content or change accounts?

The documented workflows are read-only. They do not log in, publish posts, send comments, like content, or modify accounts.

Do I need an MCP server?

No additional MCP server is required when your agent can run the documented direct CLI commands. Corresponding MCP tool names are also listed.

What happens when a request returns partial results?

Keep retrieved items and errors, then resume with the returned continuation token and original query. Do not automatically restart collection.

Can all platforms use the same filters?

No. Supported identifiers, date filters, sorting, and pagination differ by platform. Use only options documented for the selected command.

開発者情報

作成者

devinchen2014

ライセンス

不明

Skillstore リビジョン

バージョンに関する注意

作者はバージョンを宣言していません。

リポジトリ

https://github.com/devinchen2014/socialdatax-skills/tree/c14b6adea4ba2b551557115cdfffde4c17375cbf/modelscope-skills/socialdatax-content-research-assistant

参照

2d821629d9cf6def5fbc40718bb2420c989b2ca6

メンテナンスの新しさ

2026/11/2

利用状況

0 ダウンロード · 0 閲覧

ファイル構成

📁 agents/

📄 openai.yaml

📄 SKILL.md