📦
latex-posters
87建立 LaTeX 研究海報
研究海報在 LaTeX 中很難排版，也很難為列印進行校對。此技能提供範本、版面配置指引，以及適用於會議就緒海報的 PDF 檢查。
設計與創意 查看
技能 skill-creator
📦
skill-creator
內容修訂 r2 高風險 📁 檔案系統存取⚡ 包含腳本⚙️ 外部命令🌐 網路存取🔑 環境變數
建立與評估 AI 技能
建立可靠的 AI 技能需要清楚的指示、貼近實際情境的測試，以及以衡量結果為依據的反覆改進。此技能可引導草擬、基準測試、審查、描述最佳化與封裝。
支援: Claude Codex Code(CC)
安裝前請停止並請求確認。
請審查安裝計畫，並在變更檔案前取得使用者明確同意。
使用我的智慧代理安裝
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
智能體請求
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.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
Agent 可讀資源
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
測試它
正在使用「skill-creator」。 建立一個用於審查資料庫遷移的技能。
預期結果:
- 一份聚焦的技能草稿，包含觸發指引與遷移審查工作流程。
- 三個測試提示詞，涵蓋安全變更、高風險變更與不相關要求。
- 一份結合人工與自動檢查的建議評估計畫。
正在使用「skill-creator」。 使用這些審查備註改進我的文件技能。
預期結果:
一個經過修訂的技能，能將回饋一般化、移除薄弱的指示、保留原始名稱，並列出主要變更。
正在使用「skill-creator」。 第二版是否比第一版更好？
預期結果:
- 對代表性輸出進行盲測比較。
- 兩個版本的通過率、時間與 token 用量摘要。
- 根據觀察到的品質與評估變異提出建議。
安全審計
高風險v9 • 2026/7/23 開啟版本化報告
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
已掃描檔案
5,680
分析行數
28
複核項目
0
已忽略的誤報
已確認的安全問題 (6)
高
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.
高
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.
高
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.
高
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.
中
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.
中
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.
能力複核項目 (28)
這些是真實的本機能力，對此技能而言可能是預期行為，因此需要複核，但不會按已確認的惡意行為計分。
高
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.
高
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.
高
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.
高
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.
高
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
中
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.
低
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.
低
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.
低
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.
低
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.
低
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.
低
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.
低
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.
低
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.
低
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.
低
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.
低
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.
風險因素
📁 檔案系統存取 (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
⚡ 包含腳本 (9)
⚙️ 外部命令 (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
🌐 網路存取 (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
審計單位: codex 檢視審計紀錄 →
分享與引用此報告
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
複製報告連結
https://skillstore.io/skills/davila7-skill-development/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/davila7-skill-development?utm_source=security_passport_badge)HTML 徽章
<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>嵌入卡片
<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>學術引用 (APA · BibTeX · CFF)
APA 引用
davila7. (2026). skill-creator security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-skill-development/audits/9BibTeX 引用
@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"
比較變體
24 個可安裝變體每位作者的技能都保留為獨立的可安裝項目。推薦變體依 Skillstore 證據排序。
為何此變體排名第一
Skillstore 評分最高
作者 / 來源 Skillstore 評分 證據置信度 Skillstore 使用量 已更新
daviddworetzky-skill-creator
Skillstore 評分 79
證據置信度 高
Skillstore 使用量 15
已更新
2026-09-09
cesaraugustusgrob-skill-creator
Skillstore 評分 78
證據置信度 高
Skillstore 使用量 14
已更新
2026-09-09
cam10001110101-skill-creator
Skillstore 評分 75
證據置信度 高
Skillstore 使用量 22
已更新
2026-09-09
abdullahmalik17-skill-creator
Skillstore 評分 72
證據置信度 高
Skillstore 使用量 20
已更新
2026-10-20
daothihuong2111-skill-creator
Skillstore 評分 67
證據置信度 高
Skillstore 使用量 17
已更新
2026-09-09
chinchillaenterprises-skill-creator
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 15
已更新
2026-09-09
Skillstore 評分
評分依據 證據置信度: 中 77
架構
85
可維護性
87
內容
72
社群
91
規範符合度
你可以打造什麼
建立新技能
將重複性工作流程轉換為結構化指示、資源、測試，以及可供散布的技能套件。
改進現有技能
運用使用者回饋與評估結果修訂指示，並驗證變更是否能改善成果。
比較技能版本
執行基準版本與更新版本、彙整指標，並在選擇較佳版本前審查輸出。
試試這些提示
建立基本技能
為 [workflow] 建立技能。詢問必要問題、草擬 SKILL.md，並提出三個貼近實際情境的測試提示詞。
修訂現有技能
審查位於 [path] 的技能。找出指示中的缺漏、保留其名稱、修訂內容，並說明每項重要變更。
對技能進行基準測試
使用 [test prompts] 評估位於 [path] 的技能。比較技能與基準輸出、評定斷言結果，並產生審查報告。
最佳化觸發機制
為位於 [path] 的技能建立平衡的觸發測試。與我一起審查測試、執行描述最佳化，並套用表現最佳的保留測試結果。
最佳實務
- 使用能反映實際使用者用語、檔案、限制條件與邊界案例的真實提示詞。
- 在判定修訂版本較佳之前，應結合自動斷言與人工審查。
- 將保留測試與描述改進分開，以降低過度擬合。
避免
- 不要只針對少量簡單或重複的測試提示詞進行最佳化。
- 不要僅以通過率取代主觀的人工判斷。
- 在審查技能的指令碼、權限與產生的檔案之前，不要封裝或發布技能。
常見問題
這能從零開始建立技能嗎？
可以。它會蒐集需求、草擬指示、提出測試、支援反覆改進，並可封裝完成的技能。
它能改進現有技能嗎？
可以。它能保留目前的名稱、修訂指示、比較版本，並套用回饋。
它能搭配 Codex 使用嗎？
核心的草擬、審查與封裝工作流程可搭配 Codex 使用。Claude CLI 的描述最佳化仍為 Claude 專用。
是否必須使用子代理？
不需要。子代理能改善平行評估與基準測試的嚴謹度，但仍可進行較簡單的單一代理審查。
它會產生哪些檔案？
它可以產生技能指示、評估資料、評分結果、基準測試、審查頁面、回饋檔案，以及封裝後的技能封存檔。
高基準測試分數能保證品質嗎？
不能。分數取決於測試設計與斷言。仍需透過人工審查來確認實用性、安全性與泛化能力。
開發者詳細資訊
作者
davila7授權
MIT
Skillstore 修訂
r2
版本提示
作者未聲明版本。
引用
c43861a65bb95efcae259cd161c9d6f4dc7eec6f
維護新鮮度
2026/7/24
使用量
5 次下載 · 357 次瀏覽
davila7 的更多技能
查看全部📦
content-creator
87建立 SEO 就緒的行銷內容
行銷團隊需要符合品牌語氣與搜尋目標的清晰內容。此技能提供範本、分析腳本與平台指引，協助可重複的內容製作。
寫作與內容 查看
📦
treatment-plans
86建立結構化醫療治療計畫
臨床治療計畫往往會變得不一致、冗長或難以審查。此技能提供聚焦的範本、可衡量的目標、時程，以及本機品質檢查。
文件 查看
📦
clinical-reports
86建立結構化臨床報告
臨床團隊需要符合醫療與法規標準的清晰報告。此技能提供範本、檢查清單與驗證指引，適用於病例報告、診斷、試驗與病人紀錄。
文件 查看
📦
exploratory-data-analysis
85分析科學資料檔案
科學資料檔案很難檢查，因為每種格式儲存結構與中繼資料的方式都不同。此技能會偵測格式、剖析資料品質，並建立實用的 Markdown EDA 報告。
資料與分析 查看
📦
diffdock
85執行 DiffDock 分子對接工作流程
分子對接設定常因輸入、參數與信心分數難以對齊而失敗。此技能會引導 DiffDock 工作流程，從準備到結果檢閱。
研究與學習 查看
相關技能
查看全部📦
building-agents
85建置 Claude Code 代理
由 C0ntr0lledCha0s
建立可靠的 AI 代理需要清楚的結構描述、安全的工具，以及可重複的審查步驟。此技能會引導 Claude Code 工作流程中的代理設計、驗證、遷移與維護。
程式開發 查看
📦
agent-development
85建置 Claude Code 代理
由 Dami-Randle
若缺乏結構，設計可靠的 Claude Code 代理會很困難。此 skill 提供代理提示、觸發條件、工具與中繼資料的範本、驗證規則與範例。
程式開發 查看
📦
building-commands
84建置 Claude Code 斜線命令
由 C0ntr0lledCha0s
團隊需要可重複、易於呼叫與檢閱的 AI 工作流程。此技能可協助建立、更新、驗證並記錄 Claude Code 斜線命令。
程式開發 查看
📦
creating-issues
84建立一致的 GitHub Issue
由 C0ntr0lledCha0s
當 Issue 標題、標籤和專案中繼資料在不同儲存庫之間不一致時，團隊會浪費時間。此技能會引導 Claude、Codex 和 Claude Code 以一致方式建立 GitHub Issue。
程式開發 查看
📦
golang-performance
82透過 Profiling 優化 Go 效能
由 89jobrien
Go 服務在缺乏明確證據時，可能會變得緩慢或耗用大量記憶體。此 skill 會引導 profiling、配置分析、並行調校，以及以 benchmark 驅動的優化。
程式開發 查看
📦
powershell-expert
81建置可靠的 PowerShell 工具
由 hmohamed01
PowerShell 專案需要一致的結構、安全的參數，以及最新的模組指引。此技能可運用實用的 PowerShell 參考資料，協助建立指令碼、模組與 GUI。
程式開發 查看