OpenAgentSkillRegistry

Browse All Skills AI Skill Finder Use Cases Packs Compare

Gallery Rankings Creators

Blog Guides Reports

Docs Agent Entry API CLI

Star200+Submit Skill

Loading the next page

Browser Harness Audit Report | OpenAgentSkill | OpenAgentSkill

OpenAgentSkillRegistry

Browse All Skills AI Skill Finder Use Cases Packs Compare

Gallery Rankings Creators

Blog Guides Reports

Docs Agent Entry API CLI

Star200+Submit Skill

Skills/Browser Harness/Audit

Skill audit report

Browser Harness Audit report.

Browser Harness | Self-healing harness that enables LLMs to complete any task.

EXPERIMENTAL · REVIEWNeeds reviewGenerated Sep 17, 2026Heuristic metadata audit

90

Audit

84

Trust

100

Quality

77

Security

100

Maintain

92

Install

OpenAgentSkill Trust Score

84

The skill layer for AI agents: discover, compare, audit, and install reusable capabilities across Codex, Claude Code, Cursor, and agent runtimes.

Explore

Skills Gallery New submissions Agent Skills

More links

What Is an Agent Skill?AI Agent Skills Tasks Packs Best Skills New & Trending Workflow Recipes Use Cases Agents Agent Entry

Trust

Compare Safety Gate Skills Registry Rankings

More links

Outcome Loop Audits Official Weekly Reports Monthly Index State of Agent Skills vs skills.sh AgentSkills.io Alternative

Build

Docs About Contact API

More links

llms.txt OpenAPI CLI Creator Kit Skill Creators X Growth Kit Submit Blog Guides Activity

OpenAgentSkill Registry

Privacy ContactBuilt for agent-native discovery

Strong shortlist

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

100

17K GitHub stars

Stars/forks activity

PASS

97

17K stars, 1.7K forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

16d since push

License clarity

PASS

86

MIT

README/SKILL.md completeness

PASS

84

Metadata includes enough usage and workflow context

Dependency/runtime risk

WARN

46

command execution surface, credential or environment access

Install availability

PASS

92

npx skills add browser-use/browser-harness

Install command safety

PASS

92

standard package or runtime install path

Permission surface

FAIL

22

secrets or environment access, shell or command execution

Repository evidence

PASS

86

https://github.com/browser-use/browser-harness/blob/main/SKILL.md

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

9 Passed · 7 Needs review

Install path

92

PASS

npx skills add browser-use/browser-harness

Repository

88

PASS

https://github.com/browser-use/browser-harness/blob/main/SKILL.md

License

86

PASS

MIT

Maintenance

100

PASS

16d since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

46

FIX

command execution surface, credential or environment access

Install command safety

92

PASS

standard package or runtime install path

Permission surface

22

FIX

secrets or environment access, shell or command execution

Stars/forks activity

97

PASS

17K stars, 1.7K forks; issue activity unavailable in current metadata

Adoption

88

PASS

17K GitHub stars

Warnings

Dependency or permission surface needs review
Permission surface may require sandboxing
Permission surface needs review: secrets or environment access, shell or command execution
Dependency/runtime risk: command execution surface, credential or environment access
Permission surface: secrets or environment access, shell or command execution

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Install path

Review the report before installing into production agents.

$ npx skills add browser-use/browser-harness

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: review
Best agents: Python + AI Agents
Alternatives: 3

Open agent JSON

Signals

Audit score: 90/100
Quality: 100/100
Trust: 84/100
Install safety: 92/100
Permission surface: 22/100
Maintenance: 16d since push
Events: 126 events
GitHub stars: 17K
Last push: Aug 31, 2026

Agent safety v2

46/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Metadata combines secrets access with shell or command execution
High-risk permission hints: Shell or command execution, Secrets or environment access
46/100 agent safety score

Shell or command execution

high

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

Browser automation

medium

Skill may drive a browser or interact with web pages.

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

Filesystem access

medium

Skill may read or write project files, documents, generated artifacts, or local workspace state.

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

Firecrawl

The API to search, scrape, and interact with the web at scale. 🔥

139K Stars · Audit report

Daytona

Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

72K Stars · Audit report

Ppt Master

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images · by Hugo He

37K Stars · Audit report

High-risk permission hints: Shell or command execution, Secrets or environment access

Dependency or permission surface needs review