スキル agent-browser
📦

agent-browser

コンテンツリビジョン r1 重大 ⚙️ 外部コマンド🌐 ネットワークアクセス📁 ファイルシステムへのアクセス

AIエージェントでブラウザタスクを自動化

Webタスクでは、繰り返しのナビゲーション、フォーム入力、視覚的な確認が必要になることがよくあります。このスキルは、inference.shを通じてClaude、Codex、Claude Codeに構造化されたブラウザワークフローを提供します。

対応: Claude Codex Code(CC)
⚠️ 38 不十分

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト
Review the Skillstore skill "agent-browser" from https://skillstore.io/skills/inference-sh-0-agent-browser.md and its manifest at https://skillstore.io/api/skills/inference-sh-0-agent-browser/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/inference-sh-0-agent-browser.md 署名済み manifest GET /api/skills/inference-sh-0-agent-browser/manifest 署名済み lockfile GET /api/skills/inference-sh-0-agent-browser/lockfile

テストする

「agent-browser」を使用しています。 料金ページを調査し、表示されている行動喚起を取得する。

期待される結果:

  • ページを開き、主要なプラン選択、請求切り替え、営業問い合わせボタンを見つけました。
  • ビューポートのスクリーンショットを取得し、エンタープライズプランには別の問い合わせフローが必要であることを記録しました。
  • フォームは送信されず、認証済みコンテンツにはアクセスしていません。

「agent-browser」を使用しています。 承認済みのサンプルデータでテスト用問い合わせフォームに入力する。

期待される結果:

  • 現在のスナップショットから、名前、メール、メッセージ、送信コントロールを特定しました。
  • 承認済みのテスト値を入力し、フォームを送信しました。
  • 送信後に確認メッセージが表示され、セッションは閉じられました。

「agent-browser」を使用しています。 ドキュメントレビュー用の短いワークフローを記録する。

期待される結果:

  • 承認済みワークフローの前に記録を開始し、セッションが閉じられた時点で停止しました。
  • ナビゲーション手順中に重要なスクリーンショットを取得しました。
  • 期待されたボタンが表示されていなかったため、1つのステップを手動レビュー対象として記録しました。

セキュリティ監査

重大
v4 • 2026/7/5 バージョン別レポートを開く

The skill provides useful browser automation, but it relies on shell-driven infsh workflows, remote browser capture, proxy support, file upload, and page JavaScript execution. The critical issue is the pipe-to-shell installer; additional high-risk content includes cookie extraction guidance and proxy rotation for rate-limit avoidance. No prompt injection attempt was found in the reviewed files.

9
スキャンされたファイル
2,105
解析済み行数
84
レビュー項目
0
誤検知を無視

確認済みのセキュリティ上の懸念 (6)

重大
SKILL.md:17
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh && infsh login
The quick start pipes a remote installer from cli.inference.sh directly into sh. This can execute unverified network content on the user machine.
高
SKILL.md:3
Screen capture upload
description: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with e
The skill description advertises screenshots and video recording for browser sessions. Captures can include credentials or private page content and may be returned through the external service.
高
references/authentication.md:209-224
Cookie Extraction Guidance
The authentication reference shows extracting browser cookies and printing them after an authenticated session. This can expose session tokens or private account data outside the browser.
The section title and examples directly describe cookie extraction from an authenticated browser session. The risk is clear even though the code is presented as documentation.
高
references/proxy-support.md:85-129
Rate Limit Evasion via Proxy Rotation
The proxy guide includes a rate-limit avoidance workflow that rotates proxies for scraping. This supports evasion of site controls and can enable abusive automation.
The heading and example explicitly connect proxy rotation with rate-limit avoidance. This is strong intent-level evidence beyond generic proxy support.
高
SKILL.md:154-163
Local File Upload Capability
The skill supports uploading local file paths into browser file inputs. Without explicit user review, an agent could disclose local files to an external website.
The documented upload action accepts file paths and sends them through a browser form. The capability is legitimate but has a clear data disclosure risk.
中
SKILL.md:178-185references/commands.md:162-176
Arbitrary Page JavaScript Execution
The skill exposes an execute function for running custom JavaScript in the current page. This can extract page data or alter page state during authenticated sessions.
The function is documented as accepting custom JavaScript code. The browser context makes the risk concrete, but it is also an intended automation feature.
機能レビュー項目 (84)

これらは、このスキルに期待される可能性のある実際のローカル機能であるため、レビューが必要ですが、確認済みの悪意ある動作としてはカウントされません。

高
references/authentication.md:215-217
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting and printing cookie-related browser data from an authenticated session. That can expose session secrets outside the browser context.
高
references/authentication.md:218
Shell command substitution
COOKIES=$(echo $RESULT | jq -r '.result')
The authentication guide shows extracting and printing cookie-related browser data from an authenticated session. That can expose session secrets outside the browser context.
高
references/authentication.md:222-223
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting and printing cookie-related browser data from an authenticated session. That can expose session secrets outside the browser context.
高
references/proxy-support.md:152
SOCKS proxy
"proxy_url": "socks5://privacy-proxy.example.com:1080"
The proxy documentation explicitly supports SOCKS proxy routing. This can hide traffic origin and is paired with scraping and anonymity workflows in the same reference.
高
references/proxy-support.md:165
SOCKS proxy
### SOCKS5 Proxy
The proxy documentation explicitly supports SOCKS proxy routing. This can hide traffic origin and is paired with scraping and anonymity workflows in the same reference.
高
references/proxy-support.md:168
SOCKS proxy
{"proxy_url": "socks5://proxy.example.com:1080"}
The proxy documentation explicitly supports SOCKS proxy routing. This can hide traffic origin and is paired with scraping and anonymity workflows in the same reference.
高
SKILL.md:17
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh && infsh login
The URL is used to download the CLI installer that is piped into a shell. This is a real network trust and code execution risk.
中
references/authentication.md:24-26
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:51
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:52
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:70-72
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:80
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:97
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:115
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:116
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:128
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:129
Shell command substitution
ELEMENTS=$(echo $RESULT | jq -r '.elements_text')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:133
Shell command substitution
TOTP_CODE=$(oathtool --totp -b "$TOTP_SECRET")
The example invokes oathtool with a TOTP secret during automated login. This is legitimate but processes authentication secrets through shell commands.
中
references/authentication.md:153-156
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:179-181
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:202
Shell command substitution
SESSION=$(login)
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:243
Shell command substitution
export PASSWORD=$(cat /path/to/secure/password)
The example reads passwords from local files or a secrets manager into shell environment variables. This is legitimate guidance but still handles sensitive credentials in shell state.
中
references/authentication.md:246
Shell command substitution
export PASSWORD=$(vault read -field=password secret/app)
The example reads passwords from local files or a secrets manager into shell environment variables. This is legitimate guidance but still handles sensitive credentials in shell state.
中
references/authentication.md:285
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/authentication.md:292
Shell command substitution
ELEMENTS=$(echo $RESULT | jq -r '.elements_text')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
中
references/proxy-support.md:22-25
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:35-40
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:65-68
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:76
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:113-116
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:119-121
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:137-142
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:150-153
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:186-189
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:192-194
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:195
Shell command substitution
echo "IP via proxy: $(echo $RESULT | jq -r '.result')"
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:267-270
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/proxy-support.md:273
Shell command substitution
SESSION_ID=$(echo $SESSION | jq -r '.session_id')
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
中
references/snapshot-refs.md:124-126
Shell command substitution
RESULT=$(infsh app run agent-browser --function interact --session $SESSION --input '{
The documentation shows command substitution around infsh interaction examples. It is intended usage but still executes an external browser automation CLI.
中
references/snapshot-refs.md:136-138
Shell command substitution
RESULT=$(infsh app run agent-browser --function interact --session $SESSION --input '{
The documentation shows command substitution around infsh interaction examples. It is intended usage but still executes an external browser automation CLI.
中
references/video-recording.md:23-26
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:38
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:39
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:48-52
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:87-90
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:93-95
Shell command substitution
RESULT=$(infsh app run agent-browser --function interact --session $SESSION --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:97
Shell command substitution
SUCCESS=$(echo $RESULT | jq -r '.success')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:100
Shell command substitution
echo "Message: $(echo $RESULT | jq -r '.message')"
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:103
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:104
Shell command substitution
echo "Debug video: $(echo $CLOSE_RESULT | jq -r '.video')"
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:119-124
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:156
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:157
Shell command substitution
echo "Documentation video: $(echo $RESULT | jq -r '.video')"
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:168-171
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:178
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:179
Shell command substitution
VIDEO=$(echo $CLOSE_RESULT | jq -r '.video')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:195
Shell command substitution
TASK_ID=$(date +%Y%m%d-%H%M%S)
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:197-200
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:206
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
references/video-recording.md:207
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
中
SKILL.md:34-36
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
SKILL.md:37
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
SKILL.md:114-118
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
SKILL.md:213-215
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
SKILL.md:231-233
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
SKILL.md:246-249
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
SKILL.md:257
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
中
templates/authenticated-session.sh:40-42
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/authenticated-session.sh:43
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/authenticated-session.sh:1
Unix shell invocation
#!/bin/bash
This is an executable Bash template shipped with the skill. The script invokes the infsh browser automation CLI and can act on user-provided web targets.
中
templates/capture-workflow.sh:28
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:31
Shell command substitution
VIDEO=$(echo $CLOSE_RESULT | jq -r '.video // empty')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:54-59
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:60
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:63
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:64
Shell command substitution
TITLE=$(echo $RESULT | jq -r '.title')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:86
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:105-107
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:114-115
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/capture-workflow.sh:1
Unix shell invocation
#!/bin/bash
This is an executable Bash template shipped with the skill. The script invokes the infsh browser automation CLI and can act on user-provided web targets.
中
templates/form-automation.sh:30-32
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/form-automation.sh:33
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
中
templates/form-automation.sh:1
Unix shell invocation
#!/bin/bash
This is an executable Bash template shipped with the skill. The script invokes the infsh browser automation CLI and can act on user-provided web targets.
低
SKILL.md:11
Hardcoded URL
![Agentic Browser](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgjw8atdxgkrs
The Markdown loads a remote image from cloud.inference.sh. This is low severity, but it can create an external request when rendered.

リスク要因

⚙️ 外部コマンド (162)
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:15-21 SKILL.md:21-27 SKILL.md:27-32 SKILL.md:32-56 SKILL.md:56-62 SKILL.md:62-63 SKILL.md:63 SKILL.md:64 SKILL.md:65-66 SKILL.md:66-67 SKILL.md:67-73 SKILL.md:73 SKILL.md:74 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:85-86 SKILL.md:86 SKILL.md:87 SKILL.md:91-93 SKILL.md:93-99 SKILL.md:99-112 SKILL.md:112-125 SKILL.md:125-131 SKILL.md:131-137 SKILL.md:137-145 SKILL.md:145-152 SKILL.md:152-158 SKILL.md:158-164 SKILL.md:164-170 SKILL.md:170-176 SKILL.md:176-182 SKILL.md:182-187 SKILL.md:187-212 SKILL.md:212-226 SKILL.md:226-230 SKILL.md:230-241 SKILL.md:241-245 SKILL.md:245-259 SKILL.md:259-265 SKILL.md:265-266 SKILL.md:266-271 SKILL.md:271-277 SKILL.md:34-36 SKILL.md:37 SKILL.md:114-118 SKILL.md:213-215 SKILL.md:231-233 SKILL.md:246-249 SKILL.md:257 SKILL.md:32-56 SKILL.md:112-125 SKILL.md:212-226 SKILL.md:230-241 SKILL.md:245-259 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
🌐 ネットワークアクセス (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:17 SKILL.md:20 SKILL.md:35 SKILL.md:115 SKILL.md:133 SKILL.md:147 SKILL.md:148 SKILL.md:214 SKILL.md:232 SKILL.md:247 SKILL.md:281 SKILL.md:282 templates/authenticated-session.sh:118
📁 ファイルシステムへのアクセス (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

検出されたパターン

Screen capture uploadPipe to shell pattern
監査者: codex 監査履歴を表示 →
このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く
セキュリティ評価

レポートリンクをコピー

https://skillstore.io/skills/inference-sh-0-agent-browser/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-0-agent-browser/security.svg)](https://skillstore.io/skills/inference-sh-0-agent-browser?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/inference-sh-0-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-0-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/inference-sh-0-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>
学術引用 (APA · BibTeX · CFF)

APA形式の引用

inference-sh-0. (2026). agent-browser security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-0-agent-browser/audits/4

BibTeX形式の引用

@techreport{inference-sh-0-inference-sh-0-agent-browser-2026, author = {inference-sh-0}, title = {agent-browser security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/inference-sh-0-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-sh-0" date-released: "2026-07-05" url: "https://skillstore.io/skills/inference-sh-0-agent-browser/audits/4" identifiers: - type: other value: "skillstore:inference-sh-0-agent-browser:audit:4" description: "Skillstore immutable audit report identifier"

バリアントを比較

インストール可能なバリアント 19 件

各作者のスキルは個別のインストール項目として維持されます。推奨バリアントは Skillstore の証拠で順位付けされます。

このバリアントが首位の理由

Skillstore スコアが最高
supercent-io 推奨

supercent-io-agent-browser

Skillstore スコア 78
証拠の信頼度 高
Skillstore 利用状況 41
更新済み

2026-09-09

101-skills

101-skills-agent-browser

Skillstore スコア 74
証拠の信頼度 中
Skillstore 利用状況 4
更新済み

2026-09-09

vercel-labs

vercel-labs-agent-browser

Skillstore スコア 38
証拠の信頼度 高
Skillstore 利用状況 73
更新済み

2026-09-09

qu-skills

qu-skills-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 42
更新済み

2026-09-09

tul-sh

tul-sh-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 38
更新済み

2026-09-09

am-will

am-will-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 37
更新済み

2026-09-09

inference-sh-8

inference-sh-8-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 27
更新済み

2026-09-09

skillssh

skillssh-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 18
更新済み

2026-09-09

toolshell

toolshell-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 17
更新済み

2026-09-09

inference-sh-9

inference-sh-9-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 17
更新済み

2026-09-09

inferen-sh

inferen-sh-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 12
更新済み

2026-09-09

inference-sh-skills

inference-sh-skills-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 11
更新済み

2026-09-09

inference-shell

inference-shell-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 11
更新済み

2026-09-09

inferencesh

inferencesh-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 11
更新済み

2026-09-09

inference-sh-0 現在

inference-sh-0-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 11
更新済み

2026-09-09

infsh-skills

infsh-skills-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 9
更新済み

2026-09-09

inf-sh

inf-sh-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 9
更新済み

2026-09-09

inference-skills

inference-skills-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 8
更新済み

2026-09-09

halt-catch-fire

halt-catch-fire-agent-browser

Skillstore スコア 38
証拠の信頼度 中
Skillstore 利用状況 4
更新済み

2026-09-09

Skillstore スコア

このスコアの理由 証拠の信頼度: 中
45
アーキテクチャ
85
保守性
87
コンテンツ
70
コミュニティ
83
仕様準拠

作成できるもの

Webワークフローを確認する

繰り返し可能なブラウザ操作を実行し、スクリーンショットを取得して、各ステップ後の表示結果を検証します。

ページ証跡を収集する

公開ページを開き、表示テキストとリンクを抽出し、レビュー用にスクリーンショットを保存します。

管理タスクを自動化する

明示的な承認後に、認証済みツールを操作し、フォームに入力し、選択されたワークフローを記録します。

これらのプロンプトを試す

ページを開いて要約する 
agent-browserでこのURLを開き、表示されているページ状態を取得して、主要なインタラクティブ要素を要約してください: [URL]
シンプルなフォームに入力する 
agent-browserを使用してこのフォームを調査し、必要な@e refsを特定し、承認済みの値を入力して送信し、結果を報告してください: [URL]
ワークフローの証跡を取得する 
この承認済みブラウザワークフローを実行し、重要なステップ後にスクリーンショットを撮り、破壊的なステップを再試行せずに失敗したアクションを説明してください: [WORKFLOW]
認証済みセッションを監査する 
ターゲットと認証情報を私が確認した後、agent-browserを使用して承認済みの認証済みチェックを実行し、シークレットを記録せず、完了時にセッションを閉じてください。

ベストプラクティス

  • ブラウザセッションを開く前に、ターゲットURL、データの機密性、許可されたアクションを確認してください。
  • ナビゲーションや動的なページ更新の後は再度スナップショットを取得し、各アクションが現在の@e refsを使用するようにしてください。
  • 認証情報、非公開データ、規制対象コンテンツを扱う場合は、動画記録を無効にしてください。

回避

  • 検証せずにリモートインストーラーをパイプでシェルに渡して実行しないでください。
  • レート制限、アクセス制御、サイトポリシーを回避する目的でプロキシローテーションを使用しないでください。
  • 明示的な承認なしに、Cookieを抽出したり、ローカルファイルをアップロードしたり、ページJavaScriptを実行したりしないでください。

よくある質問

このスキルには別のサービスが必要ですか？
はい。inference.sh CLIと認証済みのinfshアカウントが必要です。
ログイン済みページを操作できますか？
はい。ただし、認証情報とセッションデータには明示的なユーザー承認と慎重な取り扱いが必要です。
@e refsとは何ですか？
スナップショットによって返されるコンパクトな要素参照で、エージェントがページコントロールをクリック、入力、選択できるようにします。
動画を記録できますか？
はい。記録は任意であり、機密性の高いセッションでは無効のままにしておくべきです。
プロキシをサポートしていますか？
はい。プロキシサポートはテストや企業アクセス向けに文書化されていますが、誤用するとサイトポリシーに違反する可能性があります。
任意のWebサイトに対して安全ですか？
注意して使用してください。ブラウザ自動化は、誤用すると実際の操作を引き起こしたり、ページデータを露出させたり、ファイルをアップロードしたりする可能性があります。

開発者情報

作成者

inference-sh-0

ライセンス

MIT

Skillstore リビジョン

r1

バージョンに関する注意

作者はバージョンを宣言していません。

リポジトリ

https://github.com/inference-sh-0/skills/tree/main/skills/agentic-browser/

参照

a25199bc7d6b82598536822d1738eb5d5f54025b

メンテナンスの新しさ

2026/7/18

利用状況

8 ダウンロード · 190 閲覧

ファイル構成

📁 references/

📄 authentication.md

📄 commands.md

📄 proxy-support.md

📄 snapshot-refs.md

📄 video-recording.md

📁 templates/

📄 authenticated-session.sh

📄 capture-workflow.sh

📄 form-automation.sh

📄 SKILL.md

inference-sh-0 のその他のスキル

すべて表示

関連スキル

すべて表示