技能 agent-browser
📦
agent-browser
內容修訂 r1 高風險 ⚙️ 外部命令🌐 網路存取📁 檔案系統存取
使用 Agent Refs 自動化瀏覽器工作流程
當頁面需要點擊、表單或截圖時，手動瀏覽器測試與研究會拖慢代理程式。此技能透過 belt、element refs、快照和擷取工具，讓 Claude、Codex 和 Claude Code 能夠以可重複的方式控制瀏覽器。
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 "agent-browser" from https://skillstore.io/skills/halt-catch-fire-agent-browser.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-agent-browser/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「agent-browser」。 審查公開定價頁面並擷取證據。
預期結果:
頁面已開啟，主要導覽元素已列出，完整頁面截圖已擷取，且可見的定價文字已摘要。
正在使用「agent-browser」。 使用提供的範例資料測試聯絡表單。
預期結果:
已從快照識別表單欄位，使用已核准的值填寫、提交，並根據最終頁面訊息進行驗證。
正在使用「agent-browser」。 為文件記錄一段簡短的瀏覽器工作流程。
預期結果:
瀏覽器工作階段已在游標可見的情況下錄製，主要步驟已完成，並在關閉工作階段後傳回最終影片成品。
安全審計
高風險v3 • 2026/7/6 開啟版本化報告
Most static findings are Markdown examples, documentation links, or benign shell redirection, and those were marked as false positives. Confirmed risk remains high because the skill enables remote browser automation, screenshots, video recording, authenticated data extraction, arbitrary page JavaScript, file upload, and proxy routing. I found no prompt-injection language in the reviewed skill files.
9
已掃描檔案
2,110
分析行數
56
複核項目
0
已忽略的誤報
已確認的安全問題 (6)
高
Screen capture upload
description: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with e
The skill advertises screenshots, video recording, file upload, and remote browser automation through inference.sh. These capabilities can capture and transmit sensitive page data if used on private sessions.
高
Remote Browser Capture Can Expose Sensitive Page Data
The skill uses inference.sh for browser automation and supports screenshots, videos, and file artifacts. Sensitive authenticated pages can be captured or returned through the remote service.
The front matter and video documentation directly state remote browser automation and full-session recording. The authentication guide also warns that video may capture sensitive information.
高
Authenticated Cookie Extraction Guidance
The authentication guide includes a cookie extraction section that reads document cookies and prints them. This can expose session tokens or authentication state to logs or agent output.
The section title and commands clearly describe cookie extraction from an authenticated session. Cookies are sensitive credentials even when the example is instructional.
高
references/proxy-support.md:85-128references/proxy-support.md:145-153references/proxy-support.md:280-286
Proxy Guidance Encourages Rate-Limit Avoidance And Anonymity
The proxy guide includes sections for rate limit avoidance, proxy rotation, and privacy-focused proxy routing. This can enable scraping abuse or evasion of site access controls.
The guide explicitly names rate limit avoidance and privacy proxy use. It later mentions respecting rate limits, but the evasion workflow is still present.
高
Arbitrary In-Page JavaScript Execution
The skill exposes an execute function that runs custom JavaScript in the page context. This can extract DOM data, links, cookies, or other page state from sensitive sessions.
The command reference documents a general execute function and examples for extracting page text, links, and style data. This is intentional functionality with sensitive-data implications.
中
Local File Upload Capability Can Disclose Files
The interact action supports uploading local file paths to page file inputs. Without strict user approval, this can disclose local documents to arbitrary target sites.
The action table and file upload section explicitly support upload with file_paths. The risk depends on user intent, so confidence is high but not absolute.
能力複核項目 (56)
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
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting or printing cookie/session data from an authenticated browser session. Session cookies are sensitive credentials and should not be exposed in agent output or logs.
高
Shell command substitution
COOKIES=$(echo $RESULT | jq -r '.result')
The authentication guide shows extracting or printing cookie/session data from an authenticated browser session. Session cookies are sensitive credentials and should not be exposed in agent output or logs.
高
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting or printing cookie/session data from an authenticated browser session. Session cookies are sensitive credentials and should not be exposed in agent output or logs.
高
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
高
SOCKS proxy
"proxy_url": "socks5://privacy-proxy.example.com:1080"
The documentation explicitly supports SOCKS proxy routing. This can be legitimate, but it also enables anonymized traffic and bypass of normal network controls.
高
SOCKS proxy
### SOCKS5 Proxy
The documentation explicitly supports SOCKS proxy routing. This can be legitimate, but it also enables anonymized traffic and bypass of normal network controls.
高
SOCKS proxy
{"proxy_url": "socks5://proxy.example.com:1080"}
The documentation explicitly supports SOCKS proxy routing. This can be legitimate, but it also enables anonymized traffic and bypass of normal network controls.
中
Shell command substitution
TOTP_CODE=$(oathtool --totp -b "$TOTP_SECRET")
The authentication workflow touches MFA or recorded login state. This is a legitimate automation example, but mishandling it can expose authentication factors or sensitive prompts.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The authentication workflow touches MFA or recorded login state. This is a legitimate automation example, but mishandling it can expose authentication factors or sensitive prompts.
中
Shell command substitution
PROXY_INDEX=$((i % ${#PROXIES[@]}))
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
中
Shell command substitution
echo "Fetching $URL via proxy $((PROXY_INDEX + 1))"
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
中
Unix shell invocation
#!/bin/bash
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
echo "Debug video: $(echo $CLOSE_RESULT | jq -r '.video')"
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
echo "Documentation video: $(echo $RESULT | jq -r '.video')"
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
VIDEO=$(echo $CLOSE_RESULT | jq -r '.video')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function open --session new --input '{
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Unix shell invocation
#!/bin/bash
This file is an executable shell template that drives the remote browser CLI. Runnable automation scripts increase review requirements because they can browse, capture, and write artifacts.
中
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}')
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Unix shell invocation
#!/bin/bash
This file is an executable shell template that drives the remote browser CLI. Runnable automation scripts increase review requirements because they can browse, capture, and write artifacts.
中
Standard device file access
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
中
Unix shell invocation
#!/bin/bash
This file is an executable shell template that drives the remote browser CLI. Runnable automation scripts increase review requirements because they can browse, capture, and write artifacts.
低
Hardcoded URL
"http://proxy1.example.com:8080"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
"http://proxy2.example.com:8080"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
"http://proxy3.example.com:8080"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
"https://site.com/page1"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
"https://site.com/page2"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
"https://site.com/page3"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
"url": "https://whatismyip.com",
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
低
Hardcoded URL
Browser automation for AI agents via [inference.sh](https://inference.sh). Uses Playwright under the
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
低
Hardcoded URL
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
低
Hardcoded URL
- [inference.sh Sessions](https://inference.sh/docs/extend/sessions) - Session management
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
低
Hardcoded URL
- [Multi-function Apps](https://inference.sh/docs/extend/multi-function-apps) - How functions work
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
風險因素
⚙️ 外部命令 (164)
references/authentication.md:24-26 references/authentication.md:51 references/authentication.md:52 references/authentication.md:70-72 references/authentication.md:80 references/authentication.md:97 references/authentication.md:115 references/authentication.md:116 references/authentication.md:128 references/authentication.md:129 references/authentication.md:133 references/authentication.md:153-156 references/authentication.md:179-181 references/authentication.md:202 references/authentication.md:215-217 references/authentication.md:218 references/authentication.md:222-223 references/authentication.md:243 references/authentication.md:246 references/authentication.md:285 references/authentication.md:292 references/authentication.md:21 references/authentication.md:68 references/authentication.md:174 references/proxy-support.md:22-25 references/proxy-support.md:35-40 references/proxy-support.md:65-68 references/proxy-support.md:76 references/proxy-support.md:107 references/proxy-support.md:111 references/proxy-support.md:113-116 references/proxy-support.md:119-121 references/proxy-support.md:137-142 references/proxy-support.md:150-153 references/proxy-support.md:186-189 references/proxy-support.md:192-194 references/proxy-support.md:195 references/proxy-support.md:267-270 references/proxy-support.md:273 references/proxy-support.md:294 references/proxy-support.md:50 references/proxy-support.md:90 references/snapshot-refs.md:124-126 references/snapshot-refs.md:136-138 references/snapshot-refs.md:140 references/snapshot-refs.md:142 references/video-recording.md:23-26 references/video-recording.md:38 references/video-recording.md:39 references/video-recording.md:48-52 references/video-recording.md:87-90 references/video-recording.md:93-95 references/video-recording.md:97 references/video-recording.md:100 references/video-recording.md:103 references/video-recording.md:104 references/video-recording.md:119-124 references/video-recording.md:156 references/video-recording.md:157 references/video-recording.md:168-171 references/video-recording.md:178 references/video-recording.md:179 references/video-recording.md:195 references/video-recording.md:197-200 references/video-recording.md:206 references/video-recording.md:207 references/video-recording.md:84 references/video-recording.md:116 references/video-recording.md:163 references/video-recording.md:192 SKILL.md:7 SKILL.md:11 SKILL.md:17 SKILL.md:19-24 SKILL.md:24-31 SKILL.md:31-36 SKILL.md:36-60 SKILL.md:60-66 SKILL.md:66-67 SKILL.md:67 SKILL.md:68 SKILL.md:69-70 SKILL.md:70-71 SKILL.md:71-77 SKILL.md:77 SKILL.md:78 SKILL.md:79 SKILL.md:80 SKILL.md:81 SKILL.md:82 SKILL.md:83 SKILL.md:84 SKILL.md:85 SKILL.md:86 SKILL.md:87 SKILL.md:88 SKILL.md:89-90 SKILL.md:90 SKILL.md:91 SKILL.md:95-97 SKILL.md:97-103 SKILL.md:103-116 SKILL.md:116-129 SKILL.md:129-135 SKILL.md:135-141 SKILL.md:141-149 SKILL.md:149-156 SKILL.md:156-162 SKILL.md:162-168 SKILL.md:168-174 SKILL.md:174-180 SKILL.md:180-186 SKILL.md:186-191 SKILL.md:191-216 SKILL.md:216-230 SKILL.md:230-234 SKILL.md:234-245 SKILL.md:245-249 SKILL.md:249-263 SKILL.md:263-269 SKILL.md:269-270 SKILL.md:270-275 SKILL.md:275-281 SKILL.md:38-40 SKILL.md:41 SKILL.md:118-122 SKILL.md:217-219 SKILL.md:235-237 SKILL.md:250-253 SKILL.md:261 SKILL.md:36-60 SKILL.md:116-129 SKILL.md:216-230 SKILL.md:234-245 SKILL.md:249-263 templates/authenticated-session.sh:40-42 templates/authenticated-session.sh:43 templates/authenticated-session.sh:70-73 templates/authenticated-session.sh:74 templates/authenticated-session.sh:97 templates/authenticated-session.sh:98 templates/authenticated-session.sh:127-128 templates/authenticated-session.sh:130 templates/authenticated-session.sh:1 templates/capture-workflow.sh:28 templates/capture-workflow.sh:31 templates/capture-workflow.sh:54-59 templates/capture-workflow.sh:60 templates/capture-workflow.sh:63 templates/capture-workflow.sh:64 templates/capture-workflow.sh:86 templates/capture-workflow.sh:105-107 templates/capture-workflow.sh:114-115 templates/capture-workflow.sh:126-127 templates/capture-workflow.sh:132-133 templates/capture-workflow.sh:138-139 templates/capture-workflow.sh:1 templates/form-automation.sh:30-32 templates/form-automation.sh:33 templates/form-automation.sh:102 templates/form-automation.sh:104 templates/form-automation.sh:105 templates/form-automation.sh:110 templates/form-automation.sh:1
🌐 網路存取 (54)
references/authentication.md:25 references/authentication.md:71 references/authentication.md:154 references/authentication.md:180 references/authentication.md:194 references/commands.md:25 references/commands.md:56 references/proxy-support.md:23 references/proxy-support.md:24 references/proxy-support.md:36 references/proxy-support.md:37 references/proxy-support.md:54 references/proxy-support.md:55 references/proxy-support.md:56 references/proxy-support.md:66 references/proxy-support.md:94 references/proxy-support.md:95 references/proxy-support.md:96 references/proxy-support.md:100 references/proxy-support.md:101 references/proxy-support.md:102 references/proxy-support.md:138 references/proxy-support.md:139 references/proxy-support.md:151 references/proxy-support.md:161 references/proxy-support.md:162 references/proxy-support.md:175 references/proxy-support.md:187 references/proxy-support.md:188 references/proxy-support.md:252 references/proxy-support.md:259 references/proxy-support.md:152 references/proxy-support.md:165 references/proxy-support.md:168 references/video-recording.md:24 references/video-recording.md:49 references/video-recording.md:88 references/video-recording.md:120 references/video-recording.md:198 SKILL.md:11 SKILL.md:13 SKILL.md:17 SKILL.md:23 SKILL.md:39 SKILL.md:119 SKILL.md:137 SKILL.md:151 SKILL.md:152 SKILL.md:218 SKILL.md:236 SKILL.md:251 SKILL.md:285 SKILL.md:286 templates/authenticated-session.sh:118
📁 檔案系統存取 (15)
references/authentication.md:5 references/authentication.md:263 references/commands.md:3 references/commands.md:59 references/proxy-support.md:5 references/proxy-support.md:272 references/snapshot-refs.md:5 references/video-recording.md:5 references/video-recording.md:239 templates/authenticated-session.sh:30 templates/capture-workflow.sh:28 templates/capture-workflow.sh:78 templates/capture-workflow.sh:81 templates/capture-workflow.sh:149 templates/form-automation.sh:23
偵測到的模式
Screen capture upload
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/halt-catch-fire-agent-browser/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/halt-catch-fire-agent-browser?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/halt-catch-fire-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-agent-browser.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
halt-catch-fire. (2026). agent-browser security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3BibTeX 引用
@techreport{halt-catch-fire-halt-catch-fire-agent-browser-2026,
author = {halt-catch-fire},
title = {agent-browser security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3},
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: "agent-browser security audit report (audit version 3)"
version: "unspecified"
type: report
authors:
- name: "halt-catch-fire"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3"
identifiers:
- type: other
value: "skillstore:halt-catch-fire-agent-browser:audit:3"
description: "Skillstore immutable audit report identifier"
比較變體
19 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
supercent-io 推薦
supercent-io-agent-browser
Skillstore 評分 78
證據置信度 高
Skillstore 使用量 52
已更新
2026-09-09
inference-sh-8-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 32
已更新
2026-09-09
inference-sh-9-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 21
已更新
2026-09-09
inference-sh-skills-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 16
已更新
2026-09-09
inference-sh-0-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 16
已更新
2026-09-09
inference-shell-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 15
已更新
2026-09-09
inference-skills-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 14
已更新
2026-09-09
halt-catch-fire-agent-browser
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 8
已更新
2026-09-09
Skillstore 評分
評分依據 證據置信度: 中 45
架構
85
可維護性
87
內容
67
社群
83
規範符合度
你可以打造什麼
測試互動式網頁流程
執行登入、表單和導覽流程，同時擷取截圖或影片證據。
收集網頁證據
開啟頁面、擷取可見文字和連結，並儲存截圖以供審查。
記錄瀏覽器工作流程
以游標指示器錄製可重複的瀏覽器操作，用於支援或訓練教材。
試試這些提示
開啟並檢查頁面
開啟目標頁面，摘要標題和可見的互動元素，然後關閉瀏覽器工作階段。
填寫簡單表單
使用最新快照識別表單欄位，填入提供的值，提交表單，並回報結果。
擷取研究證據
開啟每個已核准的 URL，擷取完整頁面截圖，擷取可見文字和連結，並列出已儲存的成品。
自動化已驗證工作流程
使用提供的憑證和已同意的目標網站登入，在每次導覽後重新快照，完成任務，並避免錄製敏感頁面。
最佳實務
- 僅使用已核准的目標 URL，並在任務完成後關閉每個瀏覽器工作階段。
- 在導覽、表單提交、modal 變更或動態頁面更新後重新擷取快照。
- 當憑證或敏感資料可見時，停用錄製和截圖。
避免
- 請勿使用 proxy 輪換來規避速率限制或網站存取控制。
- 請勿在日誌中列印 cookies、密碼、TOTP codes 或 session tokens。
- 除非目標網站和檔案內容已明確核准，否則請勿上傳本機檔案。
常見問題
此技能使用什麼來控制瀏覽器？
它使用 belt 或 inference.sh CLI 搭配由 Playwright 支援的 agent-browser app。
它可以點擊並填寫頁面元素嗎？
可以。它使用帶有 @e refs 的快照輸出，用於點擊、填寫、選取、拖曳、上傳和按鍵輸入。
它可以錄製瀏覽器活動嗎？
可以。錄製可在工作階段開啟時啟用，影片會在工作階段關閉時傳回。
它支援已驗證的工作階段嗎？
可以。文件包含登入、OAuth、2FA 和工作階段重複使用模式。
使用者應了解哪些資料風險？
如果在私人頁面上使用，截圖、影片、頁面文字、cookies 和上傳的檔案可能會暴露敏感資訊。
代理程式應該自動安裝此技能嗎？
不應該。遠端瀏覽、擷取、proxies、JavaScript 執行和檔案上傳都需要明確的使用者核准。
開發者詳細資訊
授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
a06681402992ceae98ba04d54cfd4ab004862696
維護新鮮度
2026/7/18
使用量
2 次下載 · 0 次瀏覽