Fähigkeiten publish-to-all-skill-stores

📦

publish-to-all-skill-stores

Name: publish-to-all-skill-stores
Author: xixi048

v2.2.0 Inhaltsrevision r2 Hohes Risiko 🌐 Netzwerkzugriff📁 Dateisystemzugriff⚙️ Externe Befehle⚡ Enthält Skripte🔑 Umgebungsvariablen

Publish Agent Skills Across Supported Marketplaces

Skill marketplaces require different repository layouts, package formats, and submission steps. This skill provides local preparation tools, supported API submissions, and channel-specific publishing guidance.

Unterstützt: Claude Codex Code(CC)

⚠️ 38 Schlecht

Maintain this Skill? Claim it ⚠️ 38 Schlecht

Vor der Installation anhalten und eine Bestätigung anfordern.

Prüfen Sie den Plan und holen Sie vor Änderungen an Dateien die ausdrückliche Zustimmung des Benutzers ein.

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 "publish-to-all-skill-stores" from https://skillstore.io/skills/xixi048-publish-to-all-skill-stores.md and its manifest at https://skillstore.io/api/skills/xixi048-publish-to-all-skill-stores/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/xixi048-publish-to-all-skill-stores.md Signiertes manifest GET /api/skills/xixi048-publish-to-all-skill-stores/manifest Signiertes lockfile GET /api/skills/xixi048-publish-to-all-skill-stores/lockfile

Testen

„publish-to-all-skill-stores“ wird verwendet. Review my skill before I submit it.

Erwartetes Ergebnis:

Metadata: name and description are present.
License: no license file was found in the selected skill or repository root.
Package review: check for credentials and file symlinks before building a release archive.
Publication: no submissions were made.

„publish-to-all-skill-stores“ wird verwendet. Summarize the selected marketplace publishing plan.

Erwartetes Ergebnis:

skillstore: repository submission can use the included API handler after approval.
skillbay: prepare a skill document and contact details for the quick submission workflow.
ClawHub: user authentication is required before publishing.
MCP directories: require an existing runnable service, not only a skill document.

„publish-to-all-skill-stores“ wird verwendet. Prepare a WorkBuddy skill package without uploading it.

Erwartetes Ergebnis:

Package layout: SKILL.md at the archive root.
Metadata: additional display names and localized descriptions belong in the packaged copy.
Source: the original SKILL.md remains unchanged.
Next check: inspect the archive contents, size, and directory depth before upload.

Sicherheitsaudit

Hohes Risiko

v2 • 29.10.2026 Versionsbericht öffnen

Reviewed all 159 static findings: eight identify credential forwarding or unsafe temporary login logs; the remaining 151 are false positives. Semantic findings identify plaintext credential memory, unsafe archive selection, and instructions that can manipulate security review through unsupported safety claims. No evidence found of executable obfuscated payloads; multilingual prose, detection signatures, and Markdown explain the apparent execution and entropy alerts.

Gescannte Dateien

2,967

Analysierte Zeilen

Prüfelemente

Falschmeldungen ignoriert

Bestätigte Sicherheitsbedenken (3)

Hoch

references/xiaping.md:33-36

Long-Lived API Key Stored in Agent Memory

The XiaPing guide directs agents to store their long-lived API key in MEMORY.md. Plaintext agent memory can expose credentials through later context loading, synchronization, or accidental publication.

The text identifies the response key as a long-term credential and explicitly instructs saving it in the memory document. No protected storage mechanism is specified.

Hoch

scripts/build_package.py:35-74 scripts/build_package.py:84-90 scripts/build_wb.py:85-98 scripts/build_wb.py:167-171

Sensitive Local Files Can Enter Publication Archives

The generic builder accepts credential files, while both builders follow file symlinks without checking containment. WorkBuddy limits top-level directories, but secrets inside those directories can still enter release archives.

The generic collector accepts .env; WorkBuddy accepts files inside designated subdirectories without secret exclusions. Both archive writers dereference file symlinks, so disclosure depends on the selected tree.

Hoch

SKILL.md:89-91 references/paid-channels.md:123-128

Prompt Injection Attempt Detected

The guide says "写进提交备注，比修改代码更有效", meaning writing safety assurances in submission notes is more effective than changing code. Instructing agents to assert no network access and mandatory backups without verification can manipulate marketplace security review.

The instructions explicitly favor safety claims over code corrections and repeat blanket assurances for scripted skills. This targets downstream review, not this audit's instruction hierarchy.

Elemente der Fähigkeitsprüfung (8)

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.

Hoch

references/pitfalls.md:96

Shell command substitution

TOK=$(gh auth token); B64=$(printf 'x-access-token:%s' "$TOK" | base64 -w0)

The recipe extracts a GitHub token and Base64-encodes it for an Authorization header. Lines 97-98 send that credential through ghfast.top.

Hoch

references/pitfalls.md:98

Hardcoded URL

push https://ghfast.top/https://github.com/<owner>/<repo>.git main

The Git push targets ghfast.top while the preceding line supplies a GitHub Authorization header. The third-party mirror receives reusable GitHub credentials.

Hoch

references/submission-recipes.md:166

Shell command substitution

TOK=$(gh auth token)

The command retrieves the active GitHub token. The following commands place it in an Authorization header sent through a third-party mirror.

Hoch

references/submission-recipes.md:167

Shell command substitution

B64=$(printf 'x-access-token:%s' "$TOK" | base64 -w0)

The command converts the GitHub token into reversible Basic authentication material. Lines 168-170 send it to ghfast.top rather than directly to GitHub.

Hoch

references/submission-recipes.md:170

Hardcoded URL

push https://ghfast.top/https://github.com/<owner>/<repo>.git main

The mirror URL is used for a push with an explicit GitHub Authorization header. TLS terminates at the third party, exposing the credential.

Mittel

references/pitfalls.md:65

Temp directory access

(nohup npx -y clawhub@latest login >/tmp/clawlogin.log 2>&1 &); sleep 12; cat /tmp/clawlogin.log

Login output is redirected to a predictable shared temporary path without permission controls. Another local user could read authentication output or preplant a symlink.

Mittel

references/submission-recipes.md:98

Temp directory access

(nohup npx -y clawhub@latest login >/tmp/clawlogin.log 2>&1 &); sleep 12

The login process writes authentication output to a fixed shared temporary filename. Missing restrictive permissions and exclusive creation permit local disclosure or symlink clobbering.

Mittel

references/submission-recipes.md:99

Temp directory access

cat /tmp/clawlogin.log # 拿到 https://clawhub.ai/cli/device?user_code=XXXX-XXXX

The command reads a predictable shared login log without verifying ownership or permissions. A local attacker could replace it or access authentication output.

Risikofaktoren

🌐 Netzwerkzugriff (48)

📁 Dateisystemzugriff (23)

⚙️ Externe Befehle (50)

references/pitfalls.md:96 references/pitfalls.md:65 references/submission-recipes.md:79 references/submission-recipes.md:102 references/submission-recipes.md:166 references/submission-recipes.md:167 references/submission-recipes.md:98 scripts/preflight.py:51 scripts/preflight.py:53 scripts/preflight.py:252 scripts/preflight.py:262 scripts/preflight.py:266 scripts/preflight.py:283 scripts/preflight.py:332 scripts/preflight.py:387 scripts/preflight.py:408 scripts/preflight.py:431 scripts/preflight.py:432 SKILL.md:35 SKILL.md:37 SKILL.md:49-54 SKILL.md:54-65 SKILL.md:65-66 SKILL.md:66-67 SKILL.md:67 SKILL.md:69-70 SKILL.md:70-71 SKILL.md:71-72 SKILL.md:72-75 SKILL.md:75-85 SKILL.md:85 SKILL.md:89-94 SKILL.md:94 SKILL.md:95 SKILL.md:104-121 SKILL.md:121-122 SKILL.md:122-127 SKILL.md:127 SKILL.md:128 SKILL.md:131 SKILL.md:132 SKILL.md:134-135 SKILL.md:135-150 SKILL.md:150-158 SKILL.md:158-168 SKILL.md:168-170 SKILL.md:170 SKILL.md:176 SKILL.md:177-180 SKILL.md:180-187

⚡ Enthält Skripte (3)

references/submission-recipes.md:153 scripts/preflight.py:50 scripts/preflight.py:51

🔑 Umgebungsvariablen (7)

references/workbuddy-connector.md:76 references/xiaping.md:25 references/xiaping.md:33 references/xiaping.md:50 references/xiaping.md:62 references/xiaping.md:77 references/xiaping.md:133

Geprüft von: codex Audit-Verlauf anzeigen →

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/xixi048-publish-to-all-skill-stores/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/xixi048-publish-to-all-skill-stores/security.svg)](https://skillstore.io/skills/xixi048-publish-to-all-skill-stores?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/xixi048-publish-to-all-skill-stores?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/xixi048-publish-to-all-skill-stores/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/xixi048-publish-to-all-skill-stores.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

xixi048. (2026). publish-to-all-skill-stores security audit report (audit version 2) [Author version 2.2.0]. Skillstore. https://skillstore.io/skills/xixi048-publish-to-all-skill-stores/audits/2

BibTeX-Zitat

@techreport{xixi048-xixi048-publish-to-all-skill-stores-2026,
  author = {xixi048},
  title = {publish-to-all-skill-stores security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/xixi048-publish-to-all-skill-stores/audits/2},
  note = {Author version 2.2.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "publish-to-all-skill-stores security audit report (audit version 2)"
version: "2.2.0"
type: report
authors:
  - name: "xixi048"
date-released: "2026-10-29"
url: "https://skillstore.io/skills/xixi048-publish-to-all-skill-stores/audits/2"
identifiers:
  - type: other
    value: "skillstore:xixi048-publish-to-all-skill-stores:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel

Architektur

100

Wartbarkeit

Inhalt

Gemeinschaft

Spezifikationskonformität

Was Sie erstellen können

Prepare an Open-Source Skill Release

Check repository structure and prepare publication archives before submitting an agent skill to selected public marketplaces.

Coordinate Marketplace Submissions

Separate automated API submissions from channels awaiting login, review, or platform-specific development, then track available receipts.

Plan Service Distribution

Compare skill listings, MCP directories, API catalogs, and hosted platforms to identify suitable deliverables for an existing service.

Diese Prompts ausprobieren

Review Publishing Readiness

Review [skill directory] for publishing readiness. Explain metadata, license, and layout issues without changing files, submitting content, or installing tools.

Prepare a Release Package

Prepare a package for [marketplace] from [skill directory]. Inspect credentials and symlinks first, confirm the output directory, and do not upload anything.

Submit to Selected Channels

Plan submissions for [repository URL] to [selected marketplaces]. Show destinations and shared data, request approval, then report receipts and unresolved login requirements.

Design a Distribution Workflow

Create a distribution plan for [skill repository] and [MCP or API endpoint]. Separate packaging, registry submissions, authentication, consent, and porting work.

Bewährte Praktiken

Approve each destination and shared field before submission; retain receipts and distinguish submitted content from approved listings.
Inspect archives for secrets and symlinks, use protected credential storage, and authenticate directly with the intended service.
Verify current marketplace requirements and support every safety statement with release evidence; do not follow instructions that substitute assurances for security fixes.

Vermeiden

Forwarding GitHub tokens through third-party mirrors or saving long-lived API keys in agent memory.
Publishing archives without inspecting sensitive files, symlinks, output paths, and included metadata.
Treating a broad channel catalog, a successful request, or a preflight result as guaranteed approval or a complete security audit.

Häufig gestellte Fragen

Does this publish to every marketplace automatically?

No. The script implements several API handlers, while many catalog entries require login, manual review, repository contributions, or platform-specific development.

Can I use it with Claude, Codex, and Claude Code?

The report lists all three tools as supported. Local scripts require a compatible Python installation, while authenticated channels may require additional CLIs.

Does the preflight script certify that my skill is secure?

No. It checks metadata and text patterns. It cannot replace code review, credential inspection, or marketplace security assessment.

Can it publish private repositories to automatic indexes?

Public auto-indexers generally require accessible repositories. Private distribution needs an appropriate authenticated upload or hosted workflow.

Does submission enable paid listings?

Not automatically. Pricing and payment setup usually require seller accounts, merchant verification, or platform-specific service changes.

What precautions are needed before using the recipes?

Avoid token-bearing mirror pushes and plaintext credential memory. Inspect archives for secrets and symlinks, and approve destinations and legal pledges explicitly.