Fähigkeiten agent-browser
📦

agent-browser

Inhaltsrevision r1 Kritisch ⚙️ Externe Befehle🌐 Netzwerkzugriff📁 Dateisystemzugriff

Browser-Aufgaben mit KI-Agenten automatisieren

Webaufgaben erfordern oft wiederholte Navigation, Formulareingaben und visuelle Prüfungen. Dieser Skill gibt Claude, Codex und Claude Code über inference.sh einen strukturierten Browser-Workflow.

Unterstützt: Claude Codex Code(CC)
⚠️ 38 Schlecht

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

Agent-Anfrage
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.

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Markdown-Detailseite GET /skills/inference-sh-0-agent-browser.md Signiertes manifest GET /api/skills/inference-sh-0-agent-browser/manifest Signiertes lockfile GET /api/skills/inference-sh-0-agent-browser/lockfile

Testen

„agent-browser“ wird verwendet. Eine Preisseite prüfen und sichtbare Handlungsaufforderungen erfassen.

Erwartetes Ergebnis:

  • Die Seite wurde geöffnet und der Hauptauswahlschalter für Tarife, der Abrechnungsumschalter und die Schaltfläche zur Kontaktaufnahme mit dem Vertrieb wurden gefunden.
  • Ein Viewport-Screenshot wurde erfasst und es wurde vermerkt, dass der Enterprise-Tarif einen separaten Kontaktprozess erfordert.
  • Es wurde kein Formular übermittelt und es wurde nicht auf authentifizierte Inhalte zugegriffen.

„agent-browser“ wird verwendet. Ein Test-Kontaktformular mit freigegebenen Beispieldaten ausfüllen.

Erwartetes Ergebnis:

  • Die Felder für Name, E-Mail, Nachricht und die Absenden-Steuerung wurden aus dem aktuellen Snapshot identifiziert.
  • Die freigegebenen Testwerte wurden eingetragen und das Formular wurde abgesendet.
  • Die Bestätigungsmeldung erschien nach dem Absenden, und die Sitzung wurde geschlossen.

„agent-browser“ wird verwendet. Einen kurzen Workflow für eine Dokumentationsprüfung aufzeichnen.

Erwartetes Ergebnis:

  • Die Aufzeichnung wurde vor dem freigegebenen Workflow gestartet und beendet, als die Sitzung geschlossen wurde.
  • Während der Navigationsschritte wurden wichtige Screenshots erfasst.
  • Ein Schritt wurde zur manuellen Prüfung markiert, weil die erwartete Schaltfläche nicht sichtbar war.

Sicherheitsaudit

Kritisch
v4 • 5.7.2026 Versionsbericht öffnen

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
Gescannte Dateien
2,105
Analysierte Zeilen
84
Prüfelemente
0
Falschmeldungen ignoriert

Bestätigte Sicherheitsbedenken (6)

Kritisch
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.
Hoch
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.
Hoch
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.
Hoch
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.
Hoch
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.
Mittel
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.
Elemente der Fähigkeitsprüfung (84)

Dies sind echte lokale Fähigkeiten, die für diese Fähigkeit erwartet werden können; daher müssen sie überprüft werden, werden jedoch nicht als bestätigtes bösartiges Verhalten gezählt.

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

Risikofaktoren

⚙️ Externe Befehle (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
🌐 Netzwerkzugriff (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
📁 Dateisystemzugriff (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

Erkannte Muster

Screen capture uploadPipe to shell pattern
Geprüft von: codex Audit-Verlauf anzeigen →
Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen
Sicherheitsbewertung

Berichtslink kopieren

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

Markdown-Badge

[![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-Badge

<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>

Einbettungskarte

<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>
Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

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-Zitat

@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"

Varianten vergleichen

19 installierbare Varianten

Jeder Autor bleibt ein eigener installierbarer Skill. Die empfohlene Variante wird nach Skillstore-Nachweisen bewertet.

Warum diese Variante zuerst steht

Höchster Skillstore-Score
supercent-io Empfohlen

supercent-io-agent-browser

Skillstore-Score 78
Evidenzvertrauen Hoch
Skillstore-Nutzung 41
Aktualisiert

2026-09-09

101-skills

101-skills-agent-browser

Skillstore-Score 74
Evidenzvertrauen Mittel
Skillstore-Nutzung 4
Aktualisiert

2026-09-09

vercel-labs

vercel-labs-agent-browser

Skillstore-Score 38
Evidenzvertrauen Hoch
Skillstore-Nutzung 73
Aktualisiert

2026-09-09

qu-skills

qu-skills-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 42
Aktualisiert

2026-09-09

tul-sh

tul-sh-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 38
Aktualisiert

2026-09-09

am-will

am-will-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 37
Aktualisiert

2026-09-09

inference-sh-8

inference-sh-8-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 27
Aktualisiert

2026-09-09

skillssh

skillssh-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 18
Aktualisiert

2026-09-09

toolshell

toolshell-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 17
Aktualisiert

2026-09-09

inference-sh-9

inference-sh-9-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 17
Aktualisiert

2026-09-09

inferen-sh

inferen-sh-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 12
Aktualisiert

2026-09-09

inference-sh-skills

inference-sh-skills-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 11
Aktualisiert

2026-09-09

inference-shell

inference-shell-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 11
Aktualisiert

2026-09-09

inferencesh

inferencesh-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 11
Aktualisiert

2026-09-09

inference-sh-0 Aktuell

inference-sh-0-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 11
Aktualisiert

2026-09-09

infsh-skills

infsh-skills-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 9
Aktualisiert

2026-09-09

inf-sh

inf-sh-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 9
Aktualisiert

2026-09-09

inference-skills

inference-skills-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 8
Aktualisiert

2026-09-09

halt-catch-fire

halt-catch-fire-agent-browser

Skillstore-Score 38
Evidenzvertrauen Mittel
Skillstore-Nutzung 4
Aktualisiert

2026-09-09

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel
45
Architektur
85
Wartbarkeit
87
Inhalt
70
Gemeinschaft
83
Spezifikationskonformität

Was Sie erstellen können

Web-Workflows prüfen

Wiederholbare Browser-Aktionen ausführen, Screenshots erfassen und sichtbare Ergebnisse nach jedem Schritt überprüfen.

Seitennachweise sammeln

Öffentliche Seiten öffnen, sichtbaren Text und Links extrahieren und Screenshots zur Prüfung speichern.

Admin-Aufgaben automatisieren

Durch authentifizierte Tools navigieren, Formulare ausfüllen und ausgewählte Workflows nach ausdrücklicher Freigabe aufzeichnen.

Diese Prompts ausprobieren

Eine Seite öffnen und zusammenfassen 
Öffne diese URL mit agent-browser, erfasse den sichtbaren Seitenstatus und fasse die wichtigsten interaktiven Elemente zusammen: [URL]
Ein einfaches Formular ausfüllen 
Verwende agent-browser, um dieses Formular zu prüfen, die benötigten @e refs zu identifizieren, die freigegebenen Werte einzutragen, es abzusenden und das Ergebnis zu melden: [URL]
Nachweise für einen Workflow erfassen 
Führe diesen freigegebenen Browser-Workflow aus, mache nach wichtigen Schritten Screenshots und erkläre jede fehlgeschlagene Aktion, ohne destruktive Schritte erneut zu versuchen: [WORKFLOW]
Eine authentifizierte Sitzung prüfen 
Nachdem ich Ziel und Zugangsdaten bestätigt habe, verwende agent-browser, um die freigegebenen authentifizierten Prüfungen durchzuführen, zeichne keine Geheimnisse auf und schließe die Sitzung danach.

Bewährte Praktiken

  • Ziel-URL, Datensensibilität und erlaubte Aktionen bestätigen, bevor eine Browser-Sitzung geöffnet wird.
  • Nach Navigation oder dynamischen Seitenaktualisierungen einen neuen Snapshot erstellen, damit jede Aktion aktuelle @e refs verwendet.
  • Videoaufzeichnung deaktivieren, wenn Zugangsdaten, private Daten oder regulierte Inhalte verarbeitet werden.

Vermeiden

  • Den Remote-Installer nicht ungeprüft über eine Pipe an die Shell ausführen.
  • Proxy-Rotation nicht verwenden, um Ratenlimits, Zugriffskontrollen oder Website-Richtlinien zu umgehen.
  • Cookies nicht extrahieren, lokale Dateien nicht hochladen und Seiten-JavaScript nicht ohne ausdrückliche Freigabe ausführen.

Häufig gestellte Fragen

Erfordert dieser Skill einen weiteren Dienst?
Ja. Er erfordert die inference.sh CLI und ein authentifiziertes infsh-Konto.
Kann er mit angemeldeten Seiten interagieren?
Ja, aber Zugangsdaten und Sitzungsdaten erfordern ausdrückliche Nutzerfreigabe und sorgfältige Handhabung.
Was sind @e refs?
Das sind kompakte Elementreferenzen, die von Snapshots zurückgegeben werden, damit Agenten Seitensteuerelemente anklicken, ausfüllen und auswählen können.
Kann er Videos aufzeichnen?
Ja. Die Aufzeichnung ist optional und sollte bei sensiblen Sitzungen deaktiviert bleiben.
Unterstützt er Proxys?
Ja. Proxy-Unterstützung ist für Tests und Unternehmenszugriff dokumentiert, aber Missbrauch kann gegen Website-Richtlinien verstoßen.
Ist er für beliebige Websites sicher?
Vorsicht ist geboten. Browser-Automatisierung kann echte Aktionen auslösen, Seitendaten offenlegen oder bei Missbrauch Dateien hochladen.

Entwicklerdetails

Lizenz

MIT

Skillstore-Revision

r1

Versionshinweis

Der Autor hat keine Version angegeben.

Repository

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

Ref.

a25199bc7d6b82598536822d1738eb5d5f54025b

Aktualität der Wartung

18.7.2026

Nutzung

8 Downloads · 190 Aufrufe

Dateistruktur

📁 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

Mehr von inference-sh-0

Alle anzeigen

Ähnliche Skills

Alle anzeigen