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 Browser 自動化瀏覽器工作流程
手動瀏覽器任務會拖慢研究、測試與營運工作。此技能為 Claude、Codex 和 Claude Code 提供可重複的瀏覽器工作階段，支援快照、操作、螢幕截圖和影片。
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/inference-skills-agent-browser.md and its manifest at https://skillstore.io/api/skills/inference-skills-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」。 開啟產品頁面並擷取關鍵互動元素。
預期結果:
簡短的頁面摘要、目前標題與 URL、螢幕截圖參照，以及可供操作的主要按鈕、連結和表單欄位。
正在使用「agent-browser」。 提交測試聯絡表單並驗證成功。
預期結果:
逐步結果，顯示填寫了哪些欄位、提交操作是否成功、最終頁面狀態，以及作為證據的螢幕截圖。
正在使用「agent-browser」。 錄製設定工作流程以供文件記錄。
預期結果:
完成的工作階段影片、最終螢幕截圖，以及導覽路徑和已變更設定的精簡摘要。
安全審計
高風險v4 • 2026/7/6 開啟版本化報告
Many static hits are false positives from Markdown code fences, relative documentation links, example URLs, and harmless /dev/null redirection. Confirmed risk remains significant because the skill runs an external browser automation CLI, supports screenshots, videos, file uploads, arbitrary page JavaScript, authenticated sessions, and SOCKS proxies. Additional semantic risks include cookie extraction guidance and proxy rotation for rate-limit avoidance.
9
已掃描檔案
2,108
分析行數
59
複核項目
0
已忽略的誤報
已確認的安全問題 (5)
高
Screen capture upload
description: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with e
The skill description advertises screenshots, video recording, and file upload. Those capabilities can expose page contents or local files if used without explicit authorization.
高
Cookie Extraction Guidance
The authentication guide includes a workflow that reads document.cookie from an authenticated browser session and prints the cookie value. This can expose session material if copied into automation or logs.
The section is explicitly titled cookie extraction and assigns cookie data from a browser execute call before echoing it. That is strong evidence of sensitive session data exposure risk.
高
Proxy Rotation for Rate Limit Avoidance
The proxy documentation includes a section for rate limit avoidance that rotates proxies while fetching multiple pages. This can enable abuse of site anti-automation controls.
The section name and example behavior directly describe rotating proxies for rate limit avoidance. Legitimate scraping is possible, but the abuse-enablement signal is clear.
高
Arbitrary Page JavaScript Execution
The skill exposes an execute function that runs caller-provided JavaScript on the current page. This can read page content, manipulate authenticated pages, and extract sensitive DOM-accessible data.
Both the command reference and main skill file document caller-supplied JavaScript execution. The risk depends on target page authorization, but the capability is explicit.
中
Sensitive Admin Session Recording
The video guide records an admin page workflow and archives the resulting video. Admin recordings can preserve sensitive page contents, identifiers, or operational actions if access controls are weak.
The example uses an admin URL and saves a recording for audit. This can be legitimate, but the evidence clearly shows sensitive workflow capture as a supported pattern.
能力複核項目 (59)
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
SOCKS proxy
"proxy_url": "socks5://privacy-proxy.example.com:1080"
The documentation explicitly supports SOCKS proxy configuration for browser traffic. SOCKS proxy support can hide origin traffic or bypass network controls, so it is a real high-risk capability.
高
SOCKS proxy
### SOCKS5 Proxy
The documentation explicitly supports SOCKS proxy configuration for browser traffic. SOCKS proxy support can hide origin traffic or bypass network controls, so it is a real high-risk capability.
高
SOCKS proxy
{"proxy_url": "socks5://proxy.example.com:1080"}
The documentation explicitly supports SOCKS proxy configuration for browser traffic. SOCKS proxy support can hide origin traffic or bypass network controls, so it is a real high-risk capability.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
TOTP_CODE=$(oathtool --totp -b "$TOTP_SECRET")
The line generates a TOTP code from a secret for automated login. This is legitimate authentication automation but handles sensitive credentials in shell.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(login)
This captures an authenticated session returned by the login helper in the surrounding workflow. The risk is contextual because it reuses browser authentication state.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
export PASSWORD=$(cat /path/to/secure/password)
The example reads a password into an environment variable from a file or secrets manager. It is presented as a best practice, but it still handles credentials in shell context.
中
Shell command substitution
export PASSWORD=$(vault read -field=password secret/app)
The example reads a password into an environment variable from a file or secrets manager. It is presented as a best practice, but it still handles credentials in shell context.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function interact --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function interact --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function interact --session $SESSION --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Unix shell invocation
#!/bin/bash
This is an executable shell template that runs the browser automation CLI and handles user-supplied URLs or sessions. It is legitimate functionality, but it is real external command execution.
中
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}')
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Unix shell invocation
#!/bin/bash
This is an executable shell template that runs the browser automation CLI and handles user-supplied URLs or sessions. It is legitimate functionality, but it is real external command execution.
中
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.
中
Unix shell invocation
#!/bin/bash
This is an executable shell template that runs the browser automation CLI and handles user-supplied URLs or sessions. It is legitimate functionality, but it is real external command execution.
風險因素
⚙️ 外部命令 (163)
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:9 SKILL.md:15 SKILL.md:17-22 SKILL.md:22-29 SKILL.md:29-34 SKILL.md:34-58 SKILL.md:58-64 SKILL.md:64-65 SKILL.md:65 SKILL.md:66 SKILL.md:67-68 SKILL.md:68-69 SKILL.md:69-75 SKILL.md:75 SKILL.md:76 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:87-88 SKILL.md:88 SKILL.md:89 SKILL.md:93-95 SKILL.md:95-101 SKILL.md:101-114 SKILL.md:114-127 SKILL.md:127-133 SKILL.md:133-139 SKILL.md:139-147 SKILL.md:147-154 SKILL.md:154-160 SKILL.md:160-166 SKILL.md:166-172 SKILL.md:172-178 SKILL.md:178-184 SKILL.md:184-189 SKILL.md:189-214 SKILL.md:214-228 SKILL.md:228-232 SKILL.md:232-243 SKILL.md:243-247 SKILL.md:247-261 SKILL.md:261-267 SKILL.md:267-268 SKILL.md:268-273 SKILL.md:273-279 SKILL.md:36-38 SKILL.md:39 SKILL.md:116-120 SKILL.md:215-217 SKILL.md:233-235 SKILL.md:248-251 SKILL.md:259 SKILL.md:34-58 SKILL.md:114-127 SKILL.md:214-228 SKILL.md:232-243 SKILL.md:247-261 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:9 SKILL.md:11 SKILL.md:15 SKILL.md:21 SKILL.md:37 SKILL.md:117 SKILL.md:135 SKILL.md:149 SKILL.md:150 SKILL.md:216 SKILL.md:234 SKILL.md:249 SKILL.md:283 SKILL.md:284 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/inference-skills-agent-browser/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/inference-skills-agent-browser?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/inference-skills-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-skills-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/inference-skills-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
inference-skills. (2026). agent-browser security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-skills-agent-browser/audits/4BibTeX 引用
@techreport{inference-skills-inference-skills-agent-browser-2026,
author = {inference-skills},
title = {agent-browser security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-skills-agent-browser/audits/4},
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 4)"
version: "unspecified"
type: report
authors:
- name: "inference-skills"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-skills-agent-browser/audits/4"
identifiers:
- type: other
value: "skillstore:inference-skills-agent-browser:audit:4"
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
68
社群
83
規範符合度
你可以打造什麼
驗證瀏覽器流程
執行表單、登入和導覽檢查，同時收集螢幕截圖或影片證據。
擷取網頁研究資料
開啟公開頁面、擷取可見文字、收集連結，並儲存頁面螢幕截圖以供審查。
自動化營運任務
在確認目標網站和憑證後，於管理工具中重複已授權的瀏覽器工作流程。
試試這些提示
開啟頁面
在新的瀏覽器工作階段中開啟此 URL，顯示可見的互動元素，並說明哪些元素 refs 對下一步很重要。
填寫表單
導覽至此表單，識別每個必填欄位，使用提供的測試資料填寫、提交，並驗證結果頁面。
擷取證據
錄製瀏覽器工作流程，執行這些步驟，在最終狀態擷取完整頁面螢幕截圖，並摘要說明變更內容。
執行已驗證的工作流程
使用已授權且已驗證的工作階段完成此工作流程。避免錄製敏感欄位，導覽後重新整理 refs，並在完成後關閉工作階段。
最佳實務
- 僅將瀏覽器自動化用於已授權的網站、帳戶和憑證。
- 在導覽、表單提交或動態頁面變更後重新整理快照。
- 當憑證、權杖、個人資料或內部記錄可能出現時，停用影片錄製。
避免
- 請勿使用代理輪換來繞過速率限制、存取控制或網站政策。
- 請勿將 Cookie、密碼、權杖或工作階段資料列印到記錄或擷取成品中。
- 除非明確指定目標網站、檔案路徑和權限，否則請勿上傳本機檔案。
常見問題
此技能需要另一個 CLI 嗎？
是。它依賴 inference.sh CLI，並透過該 CLI 使用 agent-browser app。
它可以與已登入的頁面互動嗎？
可以，但僅限使用已授權的憑證，並謹慎處理 Cookie、螢幕截圖和影片。
它可以爬取網站嗎？
它可以從頁面擷取可見文字和連結，但使用者必須遵守網站條款和速率限制。
它支援檔案上傳嗎？
可以。當提供明確的檔案路徑時，它可以將本機檔案上傳到檔案輸入元素。
為什麼元素 refs 會停止運作？
Refs 可能會在導覽或頁面更新後改變。請在下一個操作前擷取新的快照。
影片錄製對敏感工作流程安全嗎？
請謹慎使用。除非停用錄製，否則錄影可能會擷取憑證、個人資料或內部頁面。
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
2026/7/20
使用量
3 次下載 · 97 次瀏覽