Real Skill packageSource verifiedClawHub registry

Headful Browser (VNC)

Run a persistent Linux Chrome session with VNC/noVNC human takeover and capture an existing tab through CDP. Use for remote browser workflows that need manual login, MFA, or operator inspection followed by automation.

Identity and source

Publisher attributionWenlue Songregistry owner unverified by skillvetai
Functional categoryBrowser Automation & RPAautomatically inferred · 63% rule confidence
Package forminstruction with code27 recorded files
Canonical sourceClawHub registryclawhub:waylonsong:headful-browser-vnc
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 11/13/2026.claude/skills/headful-browser-vnc

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 11/13/2026.agents/skills/headful-browser-vnc

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 11/13/2026skills/headful-browser-vnc

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @waylonsong/headful-browser-vnc
clawhub inspect @waylonsong/headful-browser-vnc --version 2.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
27 / 27 inspected as text
Checked
11/13/2026, 6:40:45 AM
Scanner
0.1.3
Policy
1.0.3
6 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • browser control — automatically inferred
8 dependency and API indicators
  • npm: playwright 1.65.0
  • api: clawhub.ai
  • api: example.invalid
  • api: example.test
  • api: github.com
  • api: registry.npmjs.org
  • api: unrelated.example
  • api: user
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
11/12/2026, 8:42:34 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:54e59703c4363cadfc61c013d1afa22ba0fcf5513f68e871895438b281de8982
Show up to 27 recorded paths
  • CHANGELOG.md
  • config.example.env
  • LICENSE
  • LICENSE.txt
  • package-lock.json
  • package.json
  • README.docker.md
  • README.md
  • scripts/browser.sh
  • scripts/export_cookies.sh
  • scripts/export_page.sh
  • scripts/setup.sh
  • scripts/start_chrome_debug.sh
  • scripts/start_vnc.sh
  • scripts/stop_vnc.sh
  • skill-card.md
  • skill.json
  • SKILL.md
  • SOURCE.json
  • tests/browser.integration.test.js
  • tests/export.test.js
  • tests/linux_integration.py
  • tests/smoke_test.sh
  • tests/test_browser.py
  • tools/browser.py
  • tools/playwright_export.js
  • VALIDATION.md

Source changelog

Version 2.0.0 adds persistent owned browser sessions, exact existing-tab capture, cooperative operator handoff, scoped authentication exports, verified loopback listeners, and private artifacts with explicit failure reporting. Chrome sandboxing remains enabled. Executable .env loading, global process kills, and incompatible Docker/systemd examples are removed. The CLI has breaking changes; see the migration guide. Local regression tests, real Chrome CDP integration, and the full Linux lifecycle CI passed.