Skills agent-browser
📦
agent-browser
Content revision r1 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access
Automate Browser Workflows With Agent Refs
Manual browser testing and research slows agents when pages require clicks, forms, or screenshots. This skill gives Claude, Codex, and Claude Code repeatable browser control through belt, element refs, snapshots, and capture tools.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "agent-browser" from https://skillstore.io/skills/halt-catch-fire-agent-browser.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-agent-browser/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "agent-browser". Review a public pricing page and capture evidence.
Expected outcome:
The page was opened, key navigation elements were listed, a full-page screenshot was captured, and visible pricing text was summarized.
Using "agent-browser". Test a contact form using provided sample data.
Expected outcome:
The form fields were identified from the snapshot, filled with the approved values, submitted, and verified against the final page message.
Using "agent-browser". Record a short browser workflow for documentation.
Expected outcome:
The browser session was recorded with cursor visibility, key steps were completed, and the final video artifact was returned after closing the session.
Security Audit
High Riskv3 • 7/6/2026 Open versioned report
Most static findings are Markdown examples, documentation links, or benign shell redirection, and those were marked as false positives. Confirmed risk remains high because the skill enables remote browser automation, screenshots, video recording, authenticated data extraction, arbitrary page JavaScript, file upload, and proxy routing. I found no prompt-injection language in the reviewed skill files.
9
Files scanned
2,110
Lines analyzed
56
Review items
0
False positives ignored
Confirmed security concerns (6)
High
Screen capture upload
description: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with e
The skill advertises screenshots, video recording, file upload, and remote browser automation through inference.sh. These capabilities can capture and transmit sensitive page data if used on private sessions.
High
Remote Browser Capture Can Expose Sensitive Page Data
The skill uses inference.sh for browser automation and supports screenshots, videos, and file artifacts. Sensitive authenticated pages can be captured or returned through the remote service.
The front matter and video documentation directly state remote browser automation and full-session recording. The authentication guide also warns that video may capture sensitive information.
High
Authenticated Cookie Extraction Guidance
The authentication guide includes a cookie extraction section that reads document cookies and prints them. This can expose session tokens or authentication state to logs or agent output.
The section title and commands clearly describe cookie extraction from an authenticated session. Cookies are sensitive credentials even when the example is instructional.
High
references/proxy-support.md:85-128references/proxy-support.md:145-153references/proxy-support.md:280-286
Proxy Guidance Encourages Rate-Limit Avoidance And Anonymity
The proxy guide includes sections for rate limit avoidance, proxy rotation, and privacy-focused proxy routing. This can enable scraping abuse or evasion of site access controls.
The guide explicitly names rate limit avoidance and privacy proxy use. It later mentions respecting rate limits, but the evasion workflow is still present.
High
Arbitrary In-Page JavaScript Execution
The skill exposes an execute function that runs custom JavaScript in the page context. This can extract DOM data, links, cookies, or other page state from sensitive sessions.
The command reference documents a general execute function and examples for extracting page text, links, and style data. This is intentional functionality with sensitive-data implications.
Medium
Local File Upload Capability Can Disclose Files
The interact action supports uploading local file paths to page file inputs. Without strict user approval, this can disclose local documents to arbitrary target sites.
The action table and file upload section explicitly support upload with file_paths. The risk depends on user intent, so confidence is high but not absolute.
Capability review items (56)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting or printing cookie/session data from an authenticated browser session. Session cookies are sensitive credentials and should not be exposed in agent output or logs.
High
Shell command substitution
COOKIES=$(echo $RESULT | jq -r '.result')
The authentication guide shows extracting or printing cookie/session data from an authenticated browser session. Session cookies are sensitive credentials and should not be exposed in agent output or logs.
High
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting or printing cookie/session data from an authenticated browser session. Session cookies are sensitive credentials and should not be exposed in agent output or logs.
High
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
High
SOCKS proxy
"proxy_url": "socks5://privacy-proxy.example.com:1080"
The documentation explicitly supports SOCKS proxy routing. This can be legitimate, but it also enables anonymized traffic and bypass of normal network controls.
High
SOCKS proxy
### SOCKS5 Proxy
The documentation explicitly supports SOCKS proxy routing. This can be legitimate, but it also enables anonymized traffic and bypass of normal network controls.
High
SOCKS proxy
{"proxy_url": "socks5://proxy.example.com:1080"}
The documentation explicitly supports SOCKS proxy routing. This can be legitimate, but it also enables anonymized traffic and bypass of normal network controls.
Medium
Shell command substitution
TOTP_CODE=$(oathtool --totp -b "$TOTP_SECRET")
The authentication workflow touches MFA or recorded login state. This is a legitimate automation example, but mishandling it can expose authentication factors or sensitive prompts.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The authentication workflow touches MFA or recorded login state. This is a legitimate automation example, but mishandling it can expose authentication factors or sensitive prompts.
Medium
Shell command substitution
PROXY_INDEX=$((i % ${#PROXIES[@]}))
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
Medium
Shell command substitution
echo "Fetching $URL via proxy $((PROXY_INDEX + 1))"
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
Medium
Shell command substitution
RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
Medium
Unix shell invocation
#!/bin/bash
This proxy workflow appears in sections for rate-limit avoidance or privacy routing. The intent can support abuse by rotating or anonymizing automated browser traffic.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
echo "Debug video: $(echo $CLOSE_RESULT | jq -r '.video')"
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
echo "Documentation video: $(echo $RESULT | jq -r '.video')"
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
VIDEO=$(echo $CLOSE_RESULT | jq -r '.video')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video workflow records browser activity and returns video artifacts. Recording is useful for debugging, but it can leak credentials or private page content if enabled on sensitive sessions.
Medium
Shell command substitution
RESULT=$(belt app run agent-browser --function open --session new --input '{
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
Medium
Shell command substitution
SESSION=$(belt app run agent-browser --function open --session new --input '{
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
Medium
Shell command substitution
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
The example runs the external browser service and captures session output. It is core functionality, but it creates a remote browsing and capture surface that needs user approval.
Medium
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Unix shell invocation
#!/bin/bash
This file is an executable shell template that drives the remote browser CLI. Runnable automation scripts increase review requirements because they can browse, capture, and write artifacts.
Medium
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}')
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Unix shell invocation
#!/bin/bash
This file is an executable shell template that drives the remote browser CLI. Runnable automation scripts increase review requirements because they can browse, capture, and write artifacts.
Medium
Standard device file access
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This runnable template executes the external infsh browser app against user-supplied pages or sessions. It is intended functionality, but it can send page content and capture artifacts to a remote service.
Medium
Unix shell invocation
#!/bin/bash
This file is an executable shell template that drives the remote browser CLI. Runnable automation scripts increase review requirements because they can browse, capture, and write artifacts.
Low
Hardcoded URL
"http://proxy1.example.com:8080"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
"http://proxy2.example.com:8080"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
"http://proxy3.example.com:8080"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
"https://site.com/page1"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
"https://site.com/page2"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
"https://site.com/page3"
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
"url": "https://whatismyip.com",
The URL is a placeholder, but it appears inside proxy rotation or anonymity examples. The surrounding workflow is risky even though the hardcoded URL itself is not live malicious infrastructure.
Low
Hardcoded URL
Browser automation for AI agents via [inference.sh](https://inference.sh). Uses Playwright under the
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
Low
Hardcoded URL
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
Low
Hardcoded URL
- [inference.sh Sessions](https://inference.sh/docs/extend/sessions) - Session management
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
Low
Hardcoded URL
- [Multi-function Apps](https://inference.sh/docs/extend/multi-function-apps) - How functions work
The URL documents a real external dependency for the skill and its installation flow. This is not malicious by itself, but it confirms network reliance on third-party services.
Risk Factors
⚙️ External commands (164)
references/authentication.md:24-26 references/authentication.md:51 references/authentication.md:52 references/authentication.md:70-72 references/authentication.md:80 references/authentication.md:97 references/authentication.md:115 references/authentication.md:116 references/authentication.md:128 references/authentication.md:129 references/authentication.md:133 references/authentication.md:153-156 references/authentication.md:179-181 references/authentication.md:202 references/authentication.md:215-217 references/authentication.md:218 references/authentication.md:222-223 references/authentication.md:243 references/authentication.md:246 references/authentication.md:285 references/authentication.md:292 references/authentication.md:21 references/authentication.md:68 references/authentication.md:174 references/proxy-support.md:22-25 references/proxy-support.md:35-40 references/proxy-support.md:65-68 references/proxy-support.md:76 references/proxy-support.md:107 references/proxy-support.md:111 references/proxy-support.md:113-116 references/proxy-support.md:119-121 references/proxy-support.md:137-142 references/proxy-support.md:150-153 references/proxy-support.md:186-189 references/proxy-support.md:192-194 references/proxy-support.md:195 references/proxy-support.md:267-270 references/proxy-support.md:273 references/proxy-support.md:294 references/proxy-support.md:50 references/proxy-support.md:90 references/snapshot-refs.md:124-126 references/snapshot-refs.md:136-138 references/snapshot-refs.md:140 references/snapshot-refs.md:142 references/video-recording.md:23-26 references/video-recording.md:38 references/video-recording.md:39 references/video-recording.md:48-52 references/video-recording.md:87-90 references/video-recording.md:93-95 references/video-recording.md:97 references/video-recording.md:100 references/video-recording.md:103 references/video-recording.md:104 references/video-recording.md:119-124 references/video-recording.md:156 references/video-recording.md:157 references/video-recording.md:168-171 references/video-recording.md:178 references/video-recording.md:179 references/video-recording.md:195 references/video-recording.md:197-200 references/video-recording.md:206 references/video-recording.md:207 references/video-recording.md:84 references/video-recording.md:116 references/video-recording.md:163 references/video-recording.md:192 SKILL.md:7 SKILL.md:11 SKILL.md:17 SKILL.md:19-24 SKILL.md:24-31 SKILL.md:31-36 SKILL.md:36-60 SKILL.md:60-66 SKILL.md:66-67 SKILL.md:67 SKILL.md:68 SKILL.md:69-70 SKILL.md:70-71 SKILL.md:71-77 SKILL.md:77 SKILL.md:78 SKILL.md:79 SKILL.md:80 SKILL.md:81 SKILL.md:82 SKILL.md:83 SKILL.md:84 SKILL.md:85 SKILL.md:86 SKILL.md:87 SKILL.md:88 SKILL.md:89-90 SKILL.md:90 SKILL.md:91 SKILL.md:95-97 SKILL.md:97-103 SKILL.md:103-116 SKILL.md:116-129 SKILL.md:129-135 SKILL.md:135-141 SKILL.md:141-149 SKILL.md:149-156 SKILL.md:156-162 SKILL.md:162-168 SKILL.md:168-174 SKILL.md:174-180 SKILL.md:180-186 SKILL.md:186-191 SKILL.md:191-216 SKILL.md:216-230 SKILL.md:230-234 SKILL.md:234-245 SKILL.md:245-249 SKILL.md:249-263 SKILL.md:263-269 SKILL.md:269-270 SKILL.md:270-275 SKILL.md:275-281 SKILL.md:38-40 SKILL.md:41 SKILL.md:118-122 SKILL.md:217-219 SKILL.md:235-237 SKILL.md:250-253 SKILL.md:261 SKILL.md:36-60 SKILL.md:116-129 SKILL.md:216-230 SKILL.md:234-245 SKILL.md:249-263 templates/authenticated-session.sh:40-42 templates/authenticated-session.sh:43 templates/authenticated-session.sh:70-73 templates/authenticated-session.sh:74 templates/authenticated-session.sh:97 templates/authenticated-session.sh:98 templates/authenticated-session.sh:127-128 templates/authenticated-session.sh:130 templates/authenticated-session.sh:1 templates/capture-workflow.sh:28 templates/capture-workflow.sh:31 templates/capture-workflow.sh:54-59 templates/capture-workflow.sh:60 templates/capture-workflow.sh:63 templates/capture-workflow.sh:64 templates/capture-workflow.sh:86 templates/capture-workflow.sh:105-107 templates/capture-workflow.sh:114-115 templates/capture-workflow.sh:126-127 templates/capture-workflow.sh:132-133 templates/capture-workflow.sh:138-139 templates/capture-workflow.sh:1 templates/form-automation.sh:30-32 templates/form-automation.sh:33 templates/form-automation.sh:102 templates/form-automation.sh:104 templates/form-automation.sh:105 templates/form-automation.sh:110 templates/form-automation.sh:1
🌐 Network access (54)
references/authentication.md:25 references/authentication.md:71 references/authentication.md:154 references/authentication.md:180 references/authentication.md:194 references/commands.md:25 references/commands.md:56 references/proxy-support.md:23 references/proxy-support.md:24 references/proxy-support.md:36 references/proxy-support.md:37 references/proxy-support.md:54 references/proxy-support.md:55 references/proxy-support.md:56 references/proxy-support.md:66 references/proxy-support.md:94 references/proxy-support.md:95 references/proxy-support.md:96 references/proxy-support.md:100 references/proxy-support.md:101 references/proxy-support.md:102 references/proxy-support.md:138 references/proxy-support.md:139 references/proxy-support.md:151 references/proxy-support.md:161 references/proxy-support.md:162 references/proxy-support.md:175 references/proxy-support.md:187 references/proxy-support.md:188 references/proxy-support.md:252 references/proxy-support.md:259 references/proxy-support.md:152 references/proxy-support.md:165 references/proxy-support.md:168 references/video-recording.md:24 references/video-recording.md:49 references/video-recording.md:88 references/video-recording.md:120 references/video-recording.md:198 SKILL.md:11 SKILL.md:13 SKILL.md:17 SKILL.md:23 SKILL.md:39 SKILL.md:119 SKILL.md:137 SKILL.md:151 SKILL.md:152 SKILL.md:218 SKILL.md:236 SKILL.md:251 SKILL.md:285 SKILL.md:286 templates/authenticated-session.sh:118
📁 Filesystem access (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
Detected Patterns
Screen capture upload
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/halt-catch-fire-agent-browser?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/halt-catch-fire-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-agent-browser.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
halt-catch-fire. (2026). agent-browser security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3BibTeX citation
@techreport{halt-catch-fire-halt-catch-fire-agent-browser-2026,
author = {halt-catch-fire},
title = {agent-browser security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-browser security audit report (audit version 3)"
version: "unspecified"
type: report
authors:
- name: "halt-catch-fire"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/halt-catch-fire-agent-browser/audits/3"
identifiers:
- type: other
value: "skillstore:halt-catch-fire-agent-browser:audit:3"
description: "Skillstore immutable audit report identifier"
Compare variants
19 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
supercent-io Recommended
supercent-io-agent-browser
Skillstore Score 78
Evidence Confidence High
Skillstore usage 30
Updated
2026-08-21
101-skills-agent-browser
Skillstore Score 74
Evidence Confidence Medium
Skillstore usage 1
Updated
2026-08-21
vercel-labs-agent-browser
Skillstore Score 38
Evidence Confidence High
Skillstore usage 66
Updated
2026-08-21
qu-skills-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 40
Updated
2026-08-21
am-will-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 36
Updated
2026-08-21
tul-sh-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 35
Updated
2026-08-21
inference-sh-8-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 25
Updated
2026-08-21
toolshell-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 16
Updated
2026-08-21
skillssh-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 16
Updated
2026-08-21
inference-sh-9-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 15
Updated
2026-08-21
inferen-sh-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-08-21
inference-shell-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-08-21
inferencesh-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-08-21
inference-sh-skills-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
inference-sh-0-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
infsh-skills-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
inf-sh-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
inference-skills-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-08-21
halt-catch-fire Current
halt-catch-fire-agent-browser
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 3
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 45
Architecture
85
Maintainability
87
Content
67
Community
83
Spec Compliance
What You Can Build
Test Interactive Web Flows
Run login, form, and navigation flows while capturing screenshots or video evidence.
Collect Web Page Evidence
Open pages, extract visible text and links, and save screenshots for review.
Document Browser Workflows
Record repeatable browser actions with cursor indicators for support or training materials.
Try These Prompts
Open And Inspect A Page
Open the target page, summarize the title and visible interactive elements, then close the browser session.
Fill A Simple Form
Use the latest snapshot to identify form fields, fill the provided values, submit the form, and report the result.
Capture Research Evidence
Open each approved URL, capture a full-page screenshot, extract visible text and links, and list the saved artifacts.
Automate An Authenticated Workflow
Use the provided credentials and consented target site to log in, re-snapshot after each navigation, complete the task, and avoid recording sensitive pages.
Best Practices
- Use only approved target URLs and close every browser session after the task.
- Re-snapshot after navigation, form submission, modal changes, or dynamic page updates.
- Disable recording and screenshots when credentials or sensitive data are visible.
Avoid
- Do not use proxy rotation to evade rate limits or site access controls.
- Do not print cookies, passwords, TOTP codes, or session tokens in logs.
- Do not upload local files unless the target site and file contents are explicitly approved.
Frequently Asked Questions
What does this skill use to control the browser?
It uses the belt or inference.sh CLI with an agent-browser app backed by Playwright.
Can it click and fill page elements?
Yes. It uses snapshot output with @e refs for clicks, fills, selects, drags, uploads, and key presses.
Can it record browser activity?
Yes. Recording can be enabled when a session opens, and the video is returned when the session closes.
Does it support authenticated sessions?
Yes. The documentation includes login, OAuth, 2FA, and session reuse patterns.
What data risk should users understand?
Screenshots, videos, page text, cookies, and uploaded files can expose sensitive information if used on private pages.
Should agents auto-install this skill?
No. Remote browsing, capture, proxies, JavaScript execution, and file uploads require explicit user approval.
Developer Details
Author
halt-catch-fireLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
2 downloads · 0 views
File structure