스킬 skill-creator
📦
skill-creator
콘텐츠 리비전 r2 높은 위험 📁 파일 시스템 접근⚡ 스크립트 포함⚙️ 외부 명령어🌐 네트워크 접근🔑 환경 변수
Crear y evaluar habilidades de IA
Crear habilidades de IA fiables requiere instrucciones claras, pruebas realistas e iteraciones basadas en métricas. Esta habilidad orienta la redacción, la evaluación comparativa, la revisión, la optimización de descripciones y el empaquetado.
지원: Claude Codex Code(CC)
설치 전에 중지하고 확인을 요청하세요.
계획을 검토하고 파일을 변경하기 전에 사용자의 명시적 동의를 받으세요.
내 에이전트로 설치
이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.
에이전트 요청
Review the Skillstore skill "skill-creator" from https://skillstore.io/skills/davila7-skill-development.md and its manifest at https://skillstore.io/api/skills/davila7-skill-development/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.
에이전트가 읽기 쉬운 리소스
AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.
테스트해 보기
"skill-creator" 사용 중입니다. Crea una habilidad para revisar migraciones de bases de datos.
예상 결과:
- Un borrador específico de la habilidad con pautas de activación y un flujo de trabajo para revisar migraciones.
- Tres prompts de prueba que abordan cambios seguros, cambios arriesgados y solicitudes irrelevantes.
- Un plan de evaluación propuesto con comprobaciones humanas y automatizadas.
"skill-creator" 사용 중입니다. Mejora mi habilidad de documentación mediante estas notas de revisión.
예상 결과:
Una habilidad revisada que generaliza los comentarios, elimina instrucciones poco sólidas, conserva el nombre original y enumera los cambios principales.
"skill-creator" 사용 중입니다. ¿Es la versión dos mejor que la versión uno?
예상 결과:
- Una comparación a ciegas de resultados representativos.
- Resúmenes de tasas de aprobación, tiempos y tokens para ambas versiones.
- Una recomendación basada en la calidad observada y la variación de las evaluaciones.
보안 감사
높은 위험v9 • 2026. 7. 23. 버전별 보고서 열기
Most findings are scanner false positives caused by Markdown backticks, CSS borders, JavaScript template literals, loopback networking, and ordinary key enumeration. Confirmed risks include unsandboxed nested Claude execution, inherited secrets, forced port termination, browser injection paths, unsafe symlink handling, and shared temporary files. Publication should wait until high-impact execution, XSS, and file disclosure issues are fixed.
18
스캔된 파일
5,680
분석된 줄 수
28
검토 항목
0
오탐 무시됨
확인된 보안 우려 사항 (6)
높음
Untrusted Content Reaches Tool-Capable Nested Agents
Skill content and raw evaluation queries are sent to Claude CLI without an explicit tool denylist. Prompt injection can influence nested agent actions.
Both paths directly interpolate untrusted text and launch Claude CLI. Neither command constrains tools or supplies a minimal environment.
높음
Embedded Review Data Can Break Out of Script Context
Serialized run data is inserted directly into a script element. Output containing a closing script tag can inject active HTML or JavaScript.
json.dumps does not escape the HTML closing-script sequence. The resulting string is inserted verbatim inside the template's script element.
높음
Raw Template Placeholders Permit HTML Injection
The workflow replaces skill name, description, and evaluation data placeholders without requiring HTML or script-context escaping.
The placeholders occupy raw HTML and JavaScript contexts, while the replacement instructions require direct substitution and specify no escaping.
높음
eval-viewer/generate_review.py:121-127eval-viewer/generate_review.py:149-202scripts/package_skill.py:93-100
Symlink Following Can Disclose Files
Viewer generation and packaging follow files found below user-selected directories. Symlinks can include files outside the intended workspace or skill root.
Path.is_file and the subsequent read or archive operation follow symlinks. No resolved-path containment check rejects targets outside the selected root.
중간
Skill Name Is Used in a Filesystem Path Without Validation
A skill name from frontmatter becomes part of a command filename. Path separators can escape the intended commands directory.
The name is concatenated into a Path without a slug check or basename normalization. The file is later written and unlinked.
중간
Evaluation Artifacts Are Not Marked as Untrusted Data
The grader reads transcripts and output files without instructions to ignore embedded commands. Adversarial outputs can manipulate grading or request unrelated tool actions.
The grader is explicitly directed to read arbitrary artifacts but receives no prompt-injection boundary. Exploitability depends on the hosting agent's tool permissions.
기능 검토 항목 (28)
이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.
높음
Python subprocess.run
result = subprocess.run(
The subprocess runs lsof, then line 298 terminates every returned PID for the selected port. A user-selected port can therefore stop an unrelated local service without confirmation.
높음
innerHTML assignment (XSS risk)
wrapper.innerHTML = htmlStr;
SheetJS converts workbook content to an HTML string that is assigned to innerHTML. A crafted workbook may place active markup into the local review page unless the generated HTML is sanitized.
높음
innerHTML assignment (XSS risk)
container.innerHTML = html;
The benchmark HTML includes several unescaped metadata and configuration values before assignment to innerHTML. A modified benchmark file can inject markup into the review page.
높음
Python subprocess.run
result = subprocess.run(
This launches Claude with a prompt containing untrusted skill content and does not disable agent tools. Prompt injection in the reviewed skill can influence the nested agent beyond description rewriting.
높음
Python subprocess.Popen
process = subprocess.Popen(
This launches Claude on raw evaluation queries with inherited credentials and no explicit tool restriction. A malicious query can request tool actions before the harness terminates the process.
중간
Python environment access
env = {k: v for k, v in os.environ.items() if k != "CLAUDECODE"}
The nested Claude process inherits every environment variable except CLAUDECODE. This unnecessarily exposes unrelated credentials to a process handling untrusted skill content.
중간
Python environment access
env = {k: v for k, v in os.environ.items() if k != "CLAUDECODE"}
Each evaluation subprocess inherits the complete environment except CLAUDECODE. Raw test prompts therefore run in a process that can access unrelated environment secrets.
중간
Ruby/shell backtick execution
- **Improving an existing skill**: the old version. Before editing, snapshot the skill (`cp -r <skil
The documented cp command contains unquoted skill and workspace placeholders. Replacing them with a path containing shell metacharacters can alter the command.
중간
Ruby/shell backtick execution
```bash
The enclosed shell command passes unquoted workspace and name placeholders. Agent substitution of untrusted path text can cause shell parsing or command injection.
중간
Ruby/shell backtick execution
```bash
The enclosed nohup command uses unquoted path placeholders and starts a server in the background. Malicious path text can alter shell execution, and interrupted workflows can leave the process running.
중간
Ruby/shell backtick execution
3. Write to a temp file (e.g., `/tmp/eval_review_<skill-name>.html`) and open it: `open /tmp/eval_re
The open command uses an unquoted skill name inside a shared temporary path. Shell metacharacters in the name can change command execution.
중간
Ruby/shell backtick execution
```bash
The optimization command uses unquoted file, skill, and model placeholders. Values containing shell syntax can change the intended command when substituted by an agent.
중간
Ruby/shell backtick execution
```bash
The packaging command uses an unquoted skill path placeholder. A crafted path can be parsed as shell syntax instead of a single argument.
중간
nohup (background persistent process)
nohup python <skill-creator-path>/eval-viewer/generate_review.py \
The workflow intentionally starts the review server with nohup in the background. If the workflow stops before cleanup, the local service remains running.
중간
Temp directory access
3. Write to a temp file (e.g., `/tmp/eval_review_<skill-name>.html`) and open it: `open /tmp/eval_re
The instruction creates a predictable HTML filename in the shared temporary directory. Existing symlinks or name collisions can redirect or replace the generated review file.
중간
Temp directory access
- **Copy to a writeable location before editing.** The installed skill path may be read-only. Copy t
The update workflow recommends a fixed skill-named directory under shared temporary storage. It does not require exclusive creation or reject an existing symlink.
중간
Temp directory access
- **If packaging manually, stage in `/tmp/` first**, then copy to the output directory -- direct wri
Manual packaging is instructed to stage files in shared temporary storage without secure directory creation. A collision or symlink can redirect staged content.
낮음
Hardcoded URL
<link rel="preconnect" href="https://fonts.googleapis.com">
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&d
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link rel="preconnect" href="https://fonts.googleapis.com">
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&d
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<script src="https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js" integrity="sha384-En
Opening the viewer loads executable SheetJS code from an external CDN. Integrity metadata limits tampering, but the page still makes an outbound third-party request.
낮음
Hardcoded URL
<link rel="preconnect" href="https://fonts.googleapis.com">
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Hardcoded URL
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&d
Opening the generated page contacts Google Fonts. This is expected presentation behavior, but it discloses network metadata and prevents fully offline operation.
낮음
Temp file creation
live_report_path = Path(tempfile.gettempdir()) / f"skill_description_report_{skill_path.name}_{times
The report uses a predictable shared temporary path based on the skill name and current second. A local attacker can pre-create a symlink and redirect the later write.
위험 요인
📁 파일 시스템 접근 (15)
agents/grader.md:83 agents/grader.md:104 scripts/aggregate_benchmark.py:377 scripts/aggregate_benchmark.py:383 scripts/package_skill.py:13 scripts/package_skill.py:39 scripts/package_skill.py:15 scripts/package_skill.py:91 scripts/run_loop.py:13 scripts/run_loop.py:274 SKILL.md:242 SKILL.md:287 SKILL.md:369 SKILL.md:440 SKILL.md:441
⚡ 스크립트 포함 (9)
⚙️ 외부 명령어 (50)
assets/eval_review.html:82 assets/eval_review.html:89-99 assets/eval_review.html:126 eval-viewer/generate_review.py:291 eval-viewer/viewer.html:709 eval-viewer/viewer.html:1109 scripts/improve_description.py:35 scripts/improve_description.py:5 scripts/improve_description.py:21 scripts/improve_description.py:161 scripts/run_eval.py:85 scripts/run_eval.py:46 SKILL.md:17 SKILL.md:75-84 SKILL.md:84-101 SKILL.md:101-108 SKILL.md:108-120 SKILL.md:120-127 SKILL.md:127-130 SKILL.md:130-135 SKILL.md:135-145 SKILL.md:145-147 SKILL.md:147-159 SKILL.md:159-161 SKILL.md:161 SKILL.md:165-167 SKILL.md:167 SKILL.md:175-182 SKILL.md:182-185 SKILL.md:185-186 SKILL.md:186 SKILL.md:188-190 SKILL.md:190-197 SKILL.md:197-201 SKILL.md:201-205 SKILL.md:205 SKILL.md:209 SKILL.md:211-217 SKILL.md:217-225 SKILL.md:225 SKILL.md:228-230 SKILL.md:230-231 SKILL.md:231 SKILL.md:234-237 SKILL.md:237-244 SKILL.md:244-245 SKILL.md:245-247 SKILL.md:247 SKILL.md:265-269 SKILL.md:269-271
🌐 네트워크 접근 (16)
assets/eval_review.html:7 assets/eval_review.html:8 assets/eval_review.html:9 eval-viewer/generate_review.py:449 eval-viewer/generate_review.py:443 eval-viewer/generate_review.py:446 eval-viewer/viewer.html:666 eval-viewer/viewer.html:1012 eval-viewer/viewer.html:1044 eval-viewer/viewer.html:7 eval-viewer/viewer.html:8 eval-viewer/viewer.html:9 eval-viewer/viewer.html:10 scripts/generate_report.py:39 scripts/generate_report.py:40 scripts/generate_report.py:41
감사자: codex 감사 이력 보기 →
이 보고서 공유 및 인용
버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.
보고서 링크 복사
https://skillstore.io/skills/davila7-skill-development/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 배지
[](https://skillstore.io/skills/davila7-skill-development?utm_source=security_passport_badge)HTML 배지
<a href="https://skillstore.io/skills/davila7-skill-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-skill-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>임베드 카드
<iframe src="https://skillstore.io/embed/skills/davila7-skill-development.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>학술 인용 (APA · BibTeX · CFF)
APA 인용
davila7. (2026). skill-creator security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-skill-development/audits/9BibTeX 인용
@techreport{davila7-davila7-skill-development-2026,
author = {davila7},
title = {skill-creator security audit report (audit version 9)},
institution = {Skillstore},
year = {2026},
number = {9},
url = {https://skillstore.io/skills/davila7-skill-development/audits/9},
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: "skill-creator security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
- name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-skill-development/audits/9"
identifiers:
- type: other
value: "skillstore:davila7-skill-development:audit:9"
description: "Skillstore immutable audit report identifier"
변형 비교
설치 가능한 변형 24개각 작성자의 스킬은 별도의 설치 항목으로 유지됩니다. 추천 변형은 Skillstore 근거로 순위가 정해집니다.
이 변형이 1위인 이유
Skillstore 점수가 가장 높음
작성자 / 소스 Skillstore 점수 증거 신뢰도 Skillstore 사용량 업데이트됨
89jobrien-skill-creator
Skillstore 점수 83
증거 신뢰도 높음
Skillstore 사용량 75
업데이트됨
2026-10-18
daviddworetzky-skill-creator
Skillstore 점수 79
증거 신뢰도 높음
Skillstore 사용량 15
업데이트됨
2026-09-09
cesaraugustusgrob-skill-creator
Skillstore 점수 78
증거 신뢰도 높음
Skillstore 사용량 14
업데이트됨
2026-09-09
cam10001110101-skill-creator
Skillstore 점수 75
증거 신뢰도 높음
Skillstore 사용량 22
업데이트됨
2026-09-09
astrabit-cpt-skill-creator
Skillstore 점수 73
증거 신뢰도 높음
Skillstore 사용량 22
업데이트됨
2026-10-25
abdullahmalik17-skill-creator
Skillstore 점수 72
증거 신뢰도 높음
Skillstore 사용량 20
업데이트됨
2026-10-20
langchain-ai-skill-creator
Skillstore 점수 67
증거 신뢰도 높음
Skillstore 사용량 27
업데이트됨
2026-09-09
daothihuong2111-skill-creator
Skillstore 점수 67
증거 신뢰도 높음
Skillstore 사용량 17
업데이트됨
2026-09-09
benderfendor-skill-creator
Skillstore 점수 66
증거 신뢰도 높음
Skillstore 사용량 33
업데이트됨
2026-09-09
chinchillaenterprises-skill-creator
Skillstore 점수 38
증거 신뢰도 중간
Skillstore 사용량 15
업데이트됨
2026-09-09
Skillstore 점수
이 점수의 이유 증거 신뢰도: 중간 77
아키텍처
85
유지보수성
87
콘텐츠
72
커뮤니티
91
사양 준수
만들 수 있는 것
Crear una nueva habilidad
Convierte un flujo de trabajo repetido en instrucciones estructuradas, recursos, pruebas y un paquete de habilidad distribuible.
Mejorar una habilidad existente
Utiliza los comentarios de los usuarios y los resultados de las evaluaciones para revisar las instrucciones y comprobar que los cambios mejoran los resultados.
Comparar versiones de una habilidad
Ejecuta las versiones de referencia y actualizadas, agrupa métricas y revisa los resultados antes de seleccionar la versión más sólida.
이 프롬프트를 사용해 보세요
Crear una habilidad básica
Crea una habilidad para [workflow]. Formula las preguntas esenciales, redacta SKILL.md y propón tres prompts de prueba realistas.
Revisar una habilidad existente
Revisa la habilidad ubicada en [path]. Identifica las carencias de las instrucciones, conserva su nombre, revisa el contenido y explica cada cambio importante.
Evaluar comparativamente una habilidad
Evalúa la habilidad ubicada en [path] mediante [test prompts]. Compara los resultados de la habilidad con los de referencia, califica las afirmaciones y genera un informe de revisión.
Optimizar la activación
Crea pruebas de activación equilibradas para la habilidad ubicada en [path]. Revísalas conmigo, ejecuta la optimización de la descripción y aplica el mejor resultado del conjunto reservado.
모범 사례
- Utiliza prompts realistas que representen el lenguaje, los archivos, las restricciones y los casos extremos de los usuarios reales.
- Combina las afirmaciones automatizadas con la revisión humana antes de decidir que una revisión es mejor.
- Mantén las pruebas reservadas separadas de la mejora de la descripción para reducir el sobreajuste.
피하기
- No optimices únicamente para un conjunto pequeño de prompts de prueba fáciles o repetitivos.
- No sustituyas el juicio humano subjetivo únicamente por tasas de aprobación.
- No empaquetes ni publiques una habilidad antes de revisar sus scripts, permisos y archivos generados.
자주 묻는 질문
¿Puede crear una habilidad desde cero?
Sí. Recopila los requisitos, redacta las instrucciones, propone pruebas, facilita las iteraciones y puede empaquetar la habilidad terminada.
¿Puede mejorar una habilidad existente?
Sí. Puede conservar el nombre actual, revisar las instrucciones, comparar versiones y aplicar comentarios.
¿Funciona con Codex?
Los flujos de trabajo principales de redacción, revisión y empaquetado pueden funcionar con Codex. La optimización de descripciones mediante Claude CLI sigue siendo específica de Claude.
¿Se requieren subagentes?
No. Mejoran la evaluación en paralelo y el rigor de las referencias, pero sigue siendo posible realizar una revisión más sencilla con un solo agente.
¿Qué archivos genera?
Puede generar instrucciones de habilidades, datos de evaluación, resultados de calificación, evaluaciones comparativas, páginas de revisión, archivos de comentarios y archivos comprimidos de habilidades empaquetadas.
¿Una puntuación alta en una evaluación comparativa garantiza la calidad?
No. Las puntuaciones dependen del diseño de las pruebas y de las afirmaciones. La revisión humana sigue siendo necesaria para evaluar la utilidad, la seguridad y la generalización.