Fähigkeiten socialdatax-sensitive-check
📦

socialdatax-sensitive-check

Inhaltsrevision r1 Mittleres Risiko ⚙️ Externe Befehle🌐 Netzwerkzugriff🔑 Umgebungsvariablen

Check Social Media Drafts for Sensitive Terms

Social media drafts can contain sensitive terms and platform-specific publication risks. This skill guides SocialDataX text checks and presents available risk signals with revision suggestions.

Unterstützt: Claude Codex Code(CC)
Maintain this Skill? Claim it ⚠️ 50 Schlecht

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

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

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Markdown-Detailseite GET /skills/devinchen2014-socialdatax-sensitive-check.md Signiertes manifest GET /api/skills/devinchen2014-socialdatax-sensitive-check/manifest Signiertes lockfile GET /api/skills/devinchen2014-socialdatax-sensitive-check/lockfile

Testen

„socialdatax-sensitive-check“ wird verwendet. Check a generic draft before submitting it to the service.

Erwartetes Ergebnis:

  • Submission paused: SocialDataX stores submitted text and detection results.
  • Please approve remote submission after removing confidential information.

„socialdatax-sensitive-check“ wird verwendet. Illustrative review: the service flags an absolute promotional claim in an approved Xiaohongshu draft.

Erwartetes Ergebnis:

  • Platform: Xiaohongshu.
  • Reported concern: an absolute promotional claim was flagged.
  • Revision suggestion: replace the absolute claim with a specific, supportable statement.
  • Publication approval is not guaranteed. These example findings are illustrative, not a live service result.

„socialdatax-sensitive-check“ wird verwendet. The service returns an insufficient-balance error.

Erwartetes Ergebnis:

  • The check did not complete because the service balance is insufficient.
  • Review billing at https://socialdatax.com/dashboard/billing.
  • Do not repeat the request until the balance issue is resolved.

Sicherheitsaudit

Mittleres Risiko
v1 • 2.11.2026 Versionsbericht öffnen

One execution finding is confirmed because the documented command automatically fetches and runs an unpinned npm package. The other 27 alerts concern Markdown, ordinary URLs, expected authentication references, or readable Chinese text; no prompt injection or encoded payload was found. Additional risks involve server-side text retention without an explicit consent step and draft exposure through command-line arguments.

2
Gescannte Dateien
94
Analysierte Zeilen
1
Prüfelemente
0
Falschmeldungen ignoriert

Bestätigte Sicherheitsbedenken (2)

Mittel
SKILL.md:19-20SKILL.md:45-46
Remote draft retention lacks an explicit consent checkpoint
The workflow requests draft submission and states that the server stores submitted text and results. It gives no explicit approval step before retaining potentially confidential drafts.
Server retention is explicitly documented, while the submission workflow has no consent checkpoint. Actual retention duration and access controls are not provided.
Mittel
SKILL.md:31-33SKILL.md:45-46
Draft text exposure through command-line arguments
The example passes the draft using --text, exposing it to process inspection and possible command logs. The no-echo assurance does not prevent argument-level disclosure.
The documented invocation places text directly in process arguments. Exposure through inspection or logging depends on the execution environment.
Elemente der Fähigkeitsprüfung (1)

Dies sind echte lokale Fähigkeiten, die für diese Fähigkeit erwartet werden können; daher müssen sie überprüft werden, werden jedoch nicht als bestätigtes bösartiges Verhalten gezählt.

Mittel
SKILL.md:30-34
Ruby/shell backtick execution
```bash
Although the matched backticks are a Markdown fence, the enclosed command runs npx -y socialdatax-skills@latest. Automatic execution of mutable registry code creates supply-chain risk.

Risikofaktoren

⚙️ Externe Befehle (17)
SKILL.md:9 SKILL.md:19 SKILL.md:24 SKILL.md:30-34 SKILL.md:34-39 SKILL.md:39-40 SKILL.md:40 SKILL.md:41-42 SKILL.md:42-45 SKILL.md:45 SKILL.md:60-62 SKILL.md:62 SKILL.md:66-75 SKILL.md:75-76 SKILL.md:76-77 SKILL.md:77-83 SKILL.md:83
🌐 Netzwerkzugriff (3)
SKILL.md:7 SKILL.md:24 SKILL.md:76
🔑 Umgebungsvariablen (6)
SKILL.md:7 SKILL.md:24 SKILL.md:66 SKILL.md:75 SKILL.md:77 SKILL.md:83
Geprüft von: codex
Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen
Sicherheitsbewertung

Berichtslink kopieren

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

Markdown-Badge

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

HTML-Badge

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

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/devinchen2014-socialdatax-sensitive-check.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

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

BibTeX-Zitat

@techreport{devinchen2014-devinchen2014-socialdatax-sensitive-check-2026, author = {devinchen2014}, title = {socialdatax-sensitive-check security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/devinchen2014-socialdatax-sensitive-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: "socialdatax-sensitive-check 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-sensitive-check/audits/1" identifiers: - type: other value: "skillstore:devinchen2014-socialdatax-sensitive-check:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel
55
Architektur
65
Wartbarkeit
87
Inhalt
65
Gemeinschaft
65
Spezifikationskonformität

Was Sie erstellen können

Review a Xiaohongshu caption

Check a nonconfidential caption for reported sensitive terms and consider suggested revisions before publishing.

Screen promotional copy

Review a Douyin promotional draft and summarize reported risk categories for an editor.

Prepare an internal review note

Check approved, redacted text using generic context and separate service findings from unresolved compliance questions.

Diese Prompts ausprobieren

Check a short draft 
Check this nonconfidential text using generic context: [draft]. Before submission, explain remote retention and ask for approval.
Review platform-specific copy 
Review [draft] for Xiaohongshu. Confirm submission approval, then report available risk indicators and suggestions without repeating the complete draft.
Compare a revised draft 
Review [original] and [revision] for Douyin after submission approval. Compare reported risks and identify remaining concerns without promising publication approval.
Run a controlled review 
Review [redacted draft] for Kuaishou after retention approval. Use an available MCP tool or an approved, pinned CLI; distinguish returned fields from interpretation.

Bewährte Praktiken

  • Remove confidential details and approve remote retention before submitting a draft.
  • Use an available MCP tool or an approved, pinned CLI version; keep API keys out of prompts and logs.
  • Choose the intended platform and review suggestions manually before publication.

Vermeiden

  • Submitting private customer data or unreleased material without authorization.
  • Running mutable package versions automatically with confidential text in command-line arguments.
  • Treating a low-risk result as guaranteed platform acceptance or legal approval.

Häufig gestellte Fragen

Which platforms are supported?
The documented contexts are generic, Xiaohongshu, Douyin, and Kuaishou.
What credentials are required?
A SocialDataX API key must be configured through SOCIALDATAX_API_KEY. Do not paste the key into prompts.
Does the check stay on my machine?
No. SocialDataX processes the text remotely and stores submitted text and structured results for history, billing, and troubleshooting.
Can this skill check images?
No. The documented version supports text checks only.
Does it publish or change my account?
The documented workflow does not log in, publish, like, comment, or modify accounts. Read-only behavior does not eliminate remote data retention.
Does a successful check guarantee compliance?
No. Results depend on the external service and available fields. Human review remains necessary for platform policies and legal obligations.

Entwicklerdetails

Lizenz

Unbekannt

Skillstore-Revision

r1

Versionshinweis

Der Autor hat keine Version angegeben.

Repository

https://github.com/devinchen2014/socialdatax-skills/tree/c14b6adea4ba2b551557115cdfffde4c17375cbf/modelscope-skills/socialdatax-sensitive-check

Ref.

2d821629d9cf6def5fbc40718bb2420c989b2ca6

Aktualität der Wartung

2.11.2026

Nutzung

0 Downloads · 0 Aufrufe

Dateistruktur

📁 agents/

📄 openai.yaml

📄 SKILL.md