技能 browsing-with-playwright
📦

browsing-with-playwright

內容修訂 r1 高風險 ⚙️ 外部命令🌐 網路存取📁 檔案系統存取

使用 Playwright MCP 自動化瀏覽

手動瀏覽器測試和資料收集可能緩慢且難以重複。此技能為 Claude、Codex 和 Claude Code 提供本機 Playwright MCP 工作流程，以進行受控的瀏覽器操作。

支援: Claude Codex Code(CC)
Maintain this Skill? Claim it ⚠️ 38 差

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 "browsing-with-playwright" from https://skillstore.io/skills/asmayaseen-browsing-with-playwright.md and its manifest at https://skillstore.io/api/skills/asmayaseen-browsing-with-playwright/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。

Markdown 詳情 GET /skills/asmayaseen-browsing-with-playwright.md 已簽名 manifest GET /api/skills/asmayaseen-browsing-with-playwright/manifest 已簽名 lockfile GET /api/skills/asmayaseen-browsing-with-playwright/lockfile

測試它

正在使用「browsing-with-playwright」。 檢查註冊頁面是否載入，且是否有電子郵件和密碼欄位。

預期結果:

頁面已成功載入。快照顯示電子郵件和密碼欄位、提交按鈕，以及條款核取方塊。已擷取螢幕截圖以供檢閱。

正在使用「browsing-with-playwright」。 使用測試值提交聯絡表單並確認結果。

預期結果:

表單已填寫並提交。頁面顯示成功訊息，且最終畫面已儲存為證據。

正在使用「browsing-with-playwright」。 從型錄頁面擷取可見的產品名稱。

預期結果:

  • 已開啟型錄頁面。
  • 已在載入後擷取頁面狀態。
  • 已傳回可見的產品名稱，並註明隱藏在分頁後方的項目。

安全審計

高風險
v10 • 2026/7/9 開啟版本化報告

Most static findings are false positives from Markdown examples, JSON Schema URLs, generated reference documentation, or fixed health-check commands. Real risks remain because the skill can launch a user-supplied stdio MCP command, send MCP requests to configured endpoints, manage local processes through /tmp PID files, and execute arbitrary Playwright code in a shared browser context.

6
已掃描檔案
1,567
分析行數
23
複核項目
0
已忽略的誤報

已確認的安全問題 (2)

高
SKILL.md:109-116
Arbitrary browser code execution capability
The skill instructs users to call browser_run_code with supplied Playwright code. This is a powerful browser automation feature that can read page content and act in the active shared browser context if misused.
The documented workflow explicitly passes a code string to browser_run_code. The risk is contextual because trusted users may need it, but untrusted prompts could abuse it.
中
SKILL.md:35-40
Shared browser context may expose session state
The skill requires --shared-browser-context so browser state persists across MCP client calls. Persistent session state can expose authenticated pages or cookies during later browser automation tasks.
The documentation clearly requires a shared browser context and advises keeping the server running for long sessions. This creates a real privacy boundary concern, although it is not inherently malicious.
能力複核項目 (23)

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
scripts/mcp-client.py:204
Python subprocess.Popen
self._process = subprocess.Popen(
StdioTransport starts a user-supplied --stdio command with shell=True. This is intended MCP functionality, but it is real arbitrary local command execution if untrusted input reaches the argument.
中
scripts/start-server.sh:9
Shell command substitution
if [ -f "$PID_FILE" ] && kill -0 $(cat "$PID_FILE") 2>/dev/null; then
The script reads a PID from a predictable /tmp file inside command substitution before passing it to kill. This is local process-control logic with limited tampering risk.
中
scripts/start-server.sh:10
Shell command substitution
echo "Playwright MCP already running on port $PORT (PID: $(cat $PID_FILE))"
The script reads a PID from a predictable /tmp file inside command substitution before passing it to kill. This is local process-control logic with limited tampering risk.
中
scripts/start-server.sh:20
Shell command substitution
if kill -0 $(cat "$PID_FILE") 2>/dev/null; then
The script reads a PID from a predictable /tmp file inside command substitution before passing it to kill. This is local process-control logic with limited tampering risk.
中
scripts/start-server.sh:21
Shell command substitution
echo "Playwright MCP started on port $PORT (PID: $(cat $PID_FILE))"
The script reads a PID from a predictable /tmp file inside command substitution before passing it to kill. This is local process-control logic with limited tampering risk.
中
scripts/start-server.sh:6
Temp directory access
PID_FILE="/tmp/playwright-mcp-${PORT}.pid"
The helper stores and reads a predictable PID file under /tmp. This is common lifecycle code, but it creates a local tampering surface.
中
scripts/stop-server.sh:9
Shell command substitution
PID=$(cat "$PID_FILE")
The script reads a PID file and uses the value for process termination. This is intended cleanup behavior with a limited local tampering risk.
中
scripts/stop-server.sh:12
Shell command substitution
python3 "$(dirname "$0")/mcp-client.py" call -u "http://localhost:${PORT}" -t browser_close -p '{}'
The script invokes a local Python MCP client and derives the script directory in shell. It is intended cleanup behavior, but it is still external command execution.
中
scripts/stop-server.sh:6
Temp directory access
PID_FILE="/tmp/playwright-mcp-${PORT}.pid"
The stop helper reads, deletes, and acts on a predictable /tmp PID file. This is normal lifecycle code but has a local tampering surface.
低
scripts/mcp-client.py:146
HTTP client library
def request(self, method: str, params: Optional[dict] = None) -> dict:
The MCP client sends JSON-RPC requests to a user-provided HTTP server URL. This is legitimate for MCP, but it is real network capability and can disclose tool parameters to that endpoint.
低
scripts/mcp-client.py:271
HTTP client library
def request(self, method: str, params: Optional[dict] = None) -> dict:
The MCP client sends JSON-RPC requests to a user-provided HTTP server URL. This is legitimate for MCP, but it is real network capability and can disclose tool parameters to that endpoint.
低
scripts/mcp-client.py:314
HTTP client library
result = self.transport.request("tools/list")
The MCP client sends JSON-RPC requests to a user-provided HTTP server URL. This is legitimate for MCP, but it is real network capability and can disclose tool parameters to that endpoint.
低
scripts/mcp-client.py:323
HTTP client library
result = self.transport.request("tools/call", params)
The MCP client sends JSON-RPC requests to a user-provided HTTP server URL. This is legitimate for MCP, but it is real network capability and can disclose tool parameters to that endpoint.
低
scripts/mcp-client.py:328
HTTP client library
result = self.transport.request("resources/list")
The MCP client sends JSON-RPC requests to a user-provided HTTP server URL. This is legitimate for MCP, but it is real network capability and can disclose tool parameters to that endpoint.
低
scripts/mcp-client.py:333
HTTP client library
result = self.transport.request("prompts/list")
The MCP client sends JSON-RPC requests to a user-provided HTTP server URL. This is legitimate for MCP, but it is real network capability and can disclose tool parameters to that endpoint.
低
scripts/mcp-client.py:33
Python HTTP libraries
from urllib.request import Request, urlopen
The imported urllib client is used to contact the configured MCP HTTP endpoint. This is expected, but it confirms runtime network access.
低
scripts/start-server.sh:9
Standard device file access
if [ -f "$PID_FILE" ] && kill -0 $(cat "$PID_FILE") 2>/dev/null; then
The helper stores and reads a predictable PID file under /tmp. This is common lifecycle code, but it creates a local tampering surface.
低
scripts/start-server.sh:20
Standard device file access
if kill -0 $(cat "$PID_FILE") 2>/dev/null; then
The helper stores and reads a predictable PID file under /tmp. This is common lifecycle code, but it creates a local tampering surface.
低
scripts/stop-server.sh:10
Standard device file access
if kill -0 "$PID" 2>/dev/null; then
The stop helper reads, deletes, and acts on a predictable /tmp PID file. This is normal lifecycle code but has a local tampering surface.
低
scripts/stop-server.sh:12
Standard device file access
python3 "$(dirname "$0")/mcp-client.py" call -u "http://localhost:${PORT}" -t browser_close -p '{}'
The stop helper reads, deletes, and acts on a predictable /tmp PID file. This is normal lifecycle code but has a local tampering surface.
低
scripts/stop-server.sh:15
Standard device file access
kill "$PID" 2>/dev/null
The stop helper reads, deletes, and acts on a predictable /tmp PID file. This is normal lifecycle code but has a local tampering surface.
低
scripts/stop-server.sh:19
Standard device file access
kill -9 "$PID" 2>/dev/null || true
The stop helper reads, deletes, and acts on a predictable /tmp PID file. This is normal lifecycle code but has a local tampering surface.
低
scripts/stop-server.sh:28
Standard device file access
pkill -f "@playwright/mcp.*--port.*${PORT}" 2>/dev/null && echo "Playwright MCP stopped" || echo "Pl
The stop helper reads, deletes, and acts on a predictable /tmp PID file. This is normal lifecycle code but has a local tampering surface.

風險因素

⚙️ 外部命令 (43)
references/playwright-tools.md:247 references/playwright-tools.md:308 references/playwright-tools.md:471-480 references/playwright-tools.md:515-533 scripts/mcp-client.py:191 scripts/mcp-client.py:204 scripts/mcp-client.py:348 scripts/mcp-client.py:371 scripts/mcp-client.py:377-379 scripts/start-server.sh:9 scripts/start-server.sh:10 scripts/start-server.sh:20 scripts/start-server.sh:21 scripts/start-server.sh:1 scripts/stop-server.sh:9 scripts/stop-server.sh:12 scripts/stop-server.sh:1 scripts/verify.py:8 SKILL.md:17-23 SKILL.md:23-26 SKILL.md:26-33 SKILL.md:33-40 SKILL.md:40-46 SKILL.md:46-53 SKILL.md:53-57 SKILL.md:57-64 SKILL.md:64-68 SKILL.md:68-70 SKILL.md:70-86 SKILL.md:86-90 SKILL.md:90-98 SKILL.md:98-102 SKILL.md:102-105 SKILL.md:105-109 SKILL.md:109-111 SKILL.md:111-114 SKILL.md:114-116 SKILL.md:116-136 SKILL.md:136-138 SKILL.md:138-142 SKILL.md:142-144 SKILL.md:144-157 SKILL.md:157-159
🌐 網路存取 (49)
references/playwright-tools.md:19 references/playwright-tools.md:56 references/playwright-tools.md:91 references/playwright-tools.md:127 references/playwright-tools.md:168 references/playwright-tools.md:199 references/playwright-tools.md:265 references/playwright-tools.md:284 references/playwright-tools.md:315 references/playwright-tools.md:368 references/playwright-tools.md:399 references/playwright-tools.md:418 references/playwright-tools.md:447 references/playwright-tools.md:478 references/playwright-tools.md:531 references/playwright-tools.md:559 references/playwright-tools.md:626 references/playwright-tools.md:675 references/playwright-tools.md:712 references/playwright-tools.md:758 references/playwright-tools.md:800 references/playwright-tools.md:838 scripts/mcp-client.py:146 scripts/mcp-client.py:271 scripts/mcp-client.py:314 scripts/mcp-client.py:323 scripts/mcp-client.py:328 scripts/mcp-client.py:333 scripts/mcp-client.py:33 scripts/mcp-client.py:10 scripts/mcp-client.py:16 scripts/mcp-client.py:20 scripts/mcp-client.py:23 scripts/stop-server.sh:12 SKILL.md:31 SKILL.md:48 SKILL.md:49 SKILL.md:52 SKILL.md:59 SKILL.md:62 SKILL.md:72 SKILL.md:76 SKILL.md:80 SKILL.md:84 SKILL.md:92 SKILL.md:96 SKILL.md:103 SKILL.md:112 SKILL.md:113
📁 檔案系統存取 (9)
scripts/start-server.sh:9 scripts/start-server.sh:20 scripts/start-server.sh:6 scripts/stop-server.sh:10 scripts/stop-server.sh:12 scripts/stop-server.sh:15 scripts/stop-server.sh:19 scripts/stop-server.sh:28 scripts/stop-server.sh:6
審計單位: claude 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。

開啟版本化報告
安全評估

複製報告連結

https://skillstore.io/skills/asmayaseen-browsing-with-playwright/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/asmayaseen-browsing-with-playwright/security.svg)](https://skillstore.io/skills/asmayaseen-browsing-with-playwright?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/asmayaseen-browsing-with-playwright?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/asmayaseen-browsing-with-playwright/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/asmayaseen-browsing-with-playwright.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

Asmayaseen. (2026). browsing-with-playwright security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/asmayaseen-browsing-with-playwright/audits/10

BibTeX 引用

@techreport{asmayaseen-asmayaseen-browsing-with-playwright-2026, author = {Asmayaseen}, title = {browsing-with-playwright security audit report (audit version 10)}, institution = {Skillstore}, year = {2026}, number = {10}, url = {https://skillstore.io/skills/asmayaseen-browsing-with-playwright/audits/10}, 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: "browsing-with-playwright security audit report (audit version 10)" version: "unspecified" type: report authors: - name: "Asmayaseen" date-released: "2026-07-09" url: "https://skillstore.io/skills/asmayaseen-browsing-with-playwright/audits/10" identifiers: - type: other value: "skillstore:asmayaseen-browsing-with-playwright:audit:10" description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據 證據置信度: 中
64
架構
85
可維護性
87
內容
70
社群
83
規範符合度

你可以打造什麼

端對端測試網頁表單

導覽至頁面、填寫欄位、提交表單、等待確認，並以螢幕截圖擷取證明。

檢查僅限瀏覽器的工作流程

使用快照、點擊、等待和螢幕截圖，了解需要 JavaScript 執行的動態頁面。

擷取可見頁面資料

開啟頁面，透過快照或瀏覽器評估收集文字，並為研究任務摘要結果。

試試這些提示

開啟頁面並回報可見內容 
使用 Playwright browser skill 開啟我提供的頁面。擷取快照、摘要可見區段，並告訴我頁面是否正確載入。
填寫並提交簡單表單 
啟動 Playwright MCP 伺服器，開啟此表單，使用我提供的值填寫欄位，提交表單，並擷取確認畫面。
偵錯動態 UI 狀態 
使用瀏覽器快照和螢幕截圖重現此 UI 問題。依照所述步驟點擊，等待每個狀態變更，並回報觀察到的行為。
執行多步驟擷取工作流程 
使用 Playwright MCP 導覽目標頁面，針對要求的資料執行安全的頁面評估，並傳回包含來源頁面的精簡結果表格。

最佳實務

  • 在點擊或輸入前先取得新的 browser_snapshot，確保元素參照為最新。
  • 瀏覽器工作完成後停止 Playwright MCP 伺服器，尤其是在已驗證的工作階段之後。
  • 僅在受信任的工作流程中使用 browser_run_code，並在簡單操作中優先使用目標明確的工具呼叫。

避免

  • 當直接 HTTP 擷取已足夠時，請勿使用此技能進行靜態下載。
  • 請勿為不相關的使用者或敏感帳號重複使用共用瀏覽器情境。
  • 請勿執行從不受信任頁面、提示或票證複製的 Playwright 程式碼。

常見問題

此技能會自動化什麼？
它透過 Playwright MCP 自動化瀏覽器導覽、點擊、輸入、表單填寫、螢幕截圖、等待和頁面擷取。
它需要本機伺服器嗎？
是。輔助指令碼會啟動本機 Playwright MCP 伺服器，而 Python 用戶端會向其傳送 MCP 請求。
它可以與 Claude Code 搭配使用嗎？
可以。報告列出 Claude Code、Claude 和 Codex 為支援的工具。
它可以瀏覽已驗證的網站嗎？
可以，只要瀏覽器工作階段已驗證。使用者應在敏感工作後關閉瀏覽器。
browser_run_code 安全嗎？
它功能強大，應僅與受信任的程式碼搭配使用。盡可能優先使用特定的瀏覽器工具。
如果伺服器停止回應，我該怎麼辦？
停止並重新啟動本機 MCP 伺服器，然後在繼續瀏覽器操作前取得新的快照。

開發者詳細資訊

作者

Asmayaseen

授權

MIT

Skillstore 修訂

r1

版本提示

作者未聲明版本。

儲存庫

https://github.com/Asmayaseen/hackathon-2/tree/main/.claude/skills/browsing-with-playwright

引用

7db9b9f06e0ab79c575b58bc48c4d8dc9849f424

維護新鮮度

2026/7/29

使用量

15 次下載 · 204 次瀏覽

檔案結構

📁 references/

📄 playwright-tools.md

📁 scripts/

📄 mcp-client.py

📄 start-server.sh

📄 stop-server.sh

📄 verify.py

📄 SKILL.md

Asmayaseen 的更多技能

查看全部

相關技能

查看全部