Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection The skill is an instruction-only wrapper describing how to use the agent-browser CLI; its requeste
Security
High Risk
Quality
Watch · 63
Install
manual only
Audit version
audit-standard-v2
Source metrics come from upstream registries/repositories. Platform metrics come from user actions on SkillTrust and are protected by dedupe/rate-limit anti-abuse rules.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection The skill is an instruction-only wrapper describing how to use the agent-browser CLI; its requested actions and artifacts are consistent with a browser automation tool, but be mindful that saved state files (cookies/storage) and arbitrary page JS can contain sensitive data when used. This skill is a set of instructions for using the agent-browser CLI (no code shipped). Before installing or using it: 1) Confirm you trust the agent-browser binary/source (SKILL.md points to a GitHub repo) — installing the CLI will download Chromium and run code on your machine. 2) Treat saved state files (auth.json) as sensitive — they contain cookies/storage that can authenticate as you; avoid loading state files from untrusted sources. 3) Be aware the tool can run JS in page context (wait --fn) and mock network requests — useful for automation but could be abused to exfiltrate data if run on sensitive sites. 4) Limit the agent's permissions and only allow invocation when necessary. If you need extra assurance, review the agent-browser project's repository and npm package before installing.
• Add explicit When to Use / Guidelines sections.
• Provide at least one concrete input-output example.
• Publish versioned changelog and update cadence.
• Document compatibility and breaking-change policy.
• Expand capability limits and boundary conditions.
Is this a security certification?
No. SkillTrust audit is advisory and should be combined with your own review controls.
Can I install directly from this page?
No one-click install is provided. Use command guidance and run in your controlled environment.
- Initial release of agent-browser-clawdbot skill. - Enables fast, headless browser automation via CLI, optimized for AI agent workflows. - Provides accessibility tree snapshots with ref-based deterministic element selection. - Supports session isolation, state persistence, and robust automation commands (navigation, interaction, data extraction, network control, and more). - Includes example workflows and best practices for efficient automation.
Official source did not expose a direct install command.
Open official docsInstall method: instruction-only
Quick install
Quick preflight
Read source docs and verify prerequisites manually.Preflight checks
Post-install signal
Installed successfully? Send an activation signal to improve ranking quality over time.
Audit score 60 / 100. Risk guidance is advisory only; review evidence before install.
• Add troubleshooting and FAQ for common failures.
• Improve discoverability through verified source channels.
• Publish usage examples to increase activation quality.
• Reduce shell/file/network scope and document least privilege.
• Expose explicit provenance, dependency pinning, and security notes.
• Provide structured install + rollback steps for each supported agent.
• Mark official/verified status and keep metadata timestamps fresh.
Moderately fresh; review release notes before install.
Audit guidance: 60 / 100 · high
Scores with similar values can still differ in confidence; use evidence and risk lines below for final install judgment.
Risk 60 · Δ +0 · Findings 5
Apr 3, 2026 · auto
Latest high risk result from audit-standard-v2.