📦

menews

Name: menews
Author: me-news

v1.0.11 Inhaltsrevision r1 Sicher 🌐 Netzwerkzugriff⚙️ Externe Befehle

Create Ranked AI News Briefings

Tracking important AI news across the day takes repeated filtering and organization. This skill builds structured Chinese briefings from configured AIMPACT and ME News feeds.

Unterstützt: Claude Codex Code(CC)

🥈 80 Silber

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 "menews" from https://skillstore.io/skills/me-news-menews.md and its manifest at https://skillstore.io/api/skills/me-news-menews/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/me-news-menews.md Signiertes manifest GET /api/skills/me-news-menews/manifest Signiertes lockfile GET /api/skills/me-news-menews/lockfile

Testen

„menews“ wird verwendet. Query the AIMPACT morning briefing.

Erwartetes Ergebnis:

AI Morning Brief | 2026.08.05

Large Models

1. Chinese headline
A concise summary of the reported facts.
Source: article link

Comment: A short trend connecting the leading stories.

„menews“ wird verwendet. Show the 24-hour AI hot-news ranking.

Erwartetes Ergebnis:

AI Hot News | Last 24 Hours

1. Highest-ranked item with category, summary, source link, and available AI score.
2. Second-ranked deduplicated item with the same fields.

Sicherheitsaudit

Sicher

v1 • 5.8.2026 Versionsbericht öffnen

The skill intentionally retrieves news from four fixed ME News API endpoints and directs agents to use curl or web_fetch. Most other alerts are markdown, example links, Unicode text, or transparent scheduling examples rather than executable or obfuscated behavior.

Gescannte Dateien

398

Analysierte Zeilen

Prüfelemente

Falschmeldungen ignoriert

Elemente der Fähigkeitsprüfung (14)

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:131

Ruby/shell backtick execution

2. **调用 API(优先 `curl`,`web_fetch` 兜底)**:按 `sources.md` 配置,优先使用 `curl` 调用 AIMPACT 数据源 API

The workflow explicitly directs the agent to invoke curl against configured API endpoints. Fixed endpoints limit injection risk, but external process and network execution are real.

Mittel

SKILL.md:132-133

Ruby/shell backtick execution

- AIMPACT AI 新闻(`curl`)

This collection step explicitly designates curl for the AIMPACT AI news feed. It represents intended external command execution, despite markdown formatting.

Mittel

SKILL.md:133-134

Ruby/shell backtick execution

- AIMPACT OpenClaw 新闻(`curl`)

This collection step explicitly designates curl for the AIMPACT OpenClaw feed. It represents intended external command execution, despite markdown formatting.

Mittel

SKILL.md:134-135

Ruby/shell backtick execution

- AIMPACT 行业大事件(`curl`)

This collection step explicitly designates curl for the AIMPACT events feed. It represents intended external command execution, despite markdown formatting.

Mittel

SKILL.md:135-136

Ruby/shell backtick execution

- MetaEra AI 快讯(`curl`)

This collection step explicitly designates curl for the MetaEra feed. It represents intended external command execution, despite markdown formatting.

Mittel

SKILL.md:136

Ruby/shell backtick execution

- 仅当 `curl` 不可用或请求失败时,才使用 `web_fetch` 对同一 URL 兜底重试(遵循下方“API 抓取规则(强约束)”)

The line directs curl use and permits web_fetch as a fallback to the same endpoint. This is real external access with a constrained destination.

Mittel

SKILL.md:150

Ruby/shell backtick execution

- `sources.md` 中所有 URL 均为 API endpoint,必须优先使用 `curl` 获取数据。

The rule explicitly requires curl to retrieve configured API endpoints. This is intentional external command and network activity.

Mittel

SKILL.md:151

Ruby/shell backtick execution

- 仅当 `curl` 不可用或请求失败时,才允许使用 `web_fetch` 对同一 URL 兜底重试。

The rule directs curl execution and permits web_fetch after failure. The same-URL restriction reduces scope but does not remove external access.

Mittel

SKILL.md:156-157

Ruby/shell backtick execution

- 建议优先使用 `curl` 调用 API endpoint

The line recommends invoking curl for API requests. This is intended external command execution, although no dynamic arguments are shown.

Mittel

SKILL.md:157

Ruby/shell backtick execution

- `web_fetch` 仅作为兜底手段(`curl` 不可用或失败时)

The line identifies web_fetch and curl as request mechanisms. It confirms intended external access while limiting the fallback condition.

Niedrig

SKILL.md:96

Hardcoded URL

| MetaEra AI 快讯 | https://agent.me.news/skill/flash/list?page=1&size=20&category=ai | API | ME News

This is a fixed ME News API endpoint that the collection workflow later instructs the agent to request. The outbound destination is explicit and purpose-related.

Niedrig

SKILL.md:97

Hardcoded URL

| Aimpact AI 新闻 | https://agent.me.news/skill/aimpact/articles?page=1&size=20&category=ai | API | ME

This is a fixed AIMPACT API endpoint that the collection workflow later instructs the agent to request. The outbound destination is explicit and purpose-related.

Niedrig

SKILL.md:98

Hardcoded URL

| Aimpact OpenClaw 新闻 | https://agent.me.news/skill/aimpact/articles?page=1&size=20&category=opencla

This is a fixed AIMPACT API endpoint that the collection workflow later instructs the agent to request. The outbound destination is explicit and purpose-related.

Niedrig

SKILL.md:99

Hardcoded URL

This is a fixed AIMPACT API endpoint that the collection workflow later instructs the agent to request. The outbound destination is explicit and purpose-related.

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

Berichtslink kopieren

https://skillstore.io/skills/me-news-menews/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/me-news-menews/security.svg)](https://skillstore.io/skills/me-news-menews?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/me-news-menews?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/me-news-menews/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/me-news-menews.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

me-news. (2026). menews security audit report (audit version 1) [Author version 1.0.11]. Skillstore. https://skillstore.io/skills/me-news-menews/audits/1

BibTeX-Zitat

@techreport{me-news-me-news-menews-2026,
  author = {me-news},
  title = {menews security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/me-news-menews/audits/1},
  note = {Author version 1.0.11}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "menews security audit report (audit version 1)"
version: "1.0.11"
type: report
authors:
  - name: "me-news"
date-released: "2026-08-05"
url: "https://skillstore.io/skills/me-news-menews/audits/1"
identifiers:
  - type: other
    value: "skillstore:me-news-menews:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel

Architektur

100

Wartbarkeit

Inhalt

Gemeinschaft

Spezifikationskonformität

Was Sie erstellen können

Prepare a Daily Research Brief

Generate a ranked morning summary of recent AI developments with source links and concise Chinese summaries.

Monitor Product and Market Changes

Review the highest-scoring model, agent, funding, safety, and product news from the last 24 hours.

Publish an Internal News Digest

Create a consistent evening report for a team and deliver it through an approved messaging channel.

Diese Prompts ausprobieren

Get the Morning Briefing

Query the AIMPACT morning briefing. Return up to ten ranked items with Chinese summaries and source links.

Review Current Hot News

Query the 24-hour hot-news ranking. Group the results by category and emphasize the five highest AI scores.

Focus on Selected Categories

Create an AI selected-news report for the last 24 hours. Prioritize agents, safety, and open-source releases while preserving source links.

Build and Deliver an Evening Digest

Generate the AIMPACT evening briefing, remove duplicate titles, rank by AI score, and send it through my configured message channel.

Bewährte Praktiken

Review source links before sharing reports or making decisions.
Confirm the intended recipients and schedule before enabling message delivery.
Use the defined report type that matches the required time window.

Vermeiden

Do not treat generated summaries as independent fact verification.
Do not add unapproved endpoints outside the configured source allowlist.
Do not enable scheduled delivery before testing the report and recipient configuration.

Häufig gestellte Fragen

Which news sources does this skill use?

It uses four configured AIMPACT and ME News API feeds for AI articles, OpenClaw news, events, and flash updates.

What report types are available?

It supports morning briefings, evening summaries, 24-hour hot-news rankings, and selected AI news reports.

Does it search the public web?

No. The workflow restricts collection to the URLs listed in its source configuration.

Can it deliver reports automatically?

Yes, but scheduling and the OpenClaw message channel must be configured separately with approved recipients and credentials.

How are stories ranked?

The skill sorts by the AI score supplied by the API when that score is available.

Does the skill verify every news claim?

No. Users should open the included source links and verify important claims independently.

Entwicklerdetails

Autor

me-news

Lizenz

MIT

Autorenversion

v1.0.11

Skillstore-Revision

Repository

https://github.com/me-news/agent-skills/tree/34400d7a68276f70f53404d8b6859ef926699cd4/skills/menews

Ref.

e5f4ac55b99872f66a36ead0049c5c56486976b8

Aktualität der Wartung

5.8.2026

Nutzung

0 Downloads · 0 Aufrufe

Dateistruktur

📄 _meta.json

📄 format.md

📄 skill-card.md

📄 SKILL.md

📄 sources.md

menews

Mit meinem Agent installieren

Agent-lesbare Ressourcen

Testen

Sicherheitsaudit

Risikofaktoren

Berichtslink kopieren

Markdown-Badge

HTML-Badge

Einbettungskarte

APA-Zitat

BibTeX-Zitat

CITATION.cff

Skillstore-Score

Was Sie erstellen können

Prepare a Daily Research Brief

Monitor Product and Market Changes

Publish an Internal News Digest

Diese Prompts ausprobieren

Bewährte Praktiken

Vermeiden

Häufig gestellte Fragen

Entwicklerdetails