No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by lightpanda-io · Codex Skill · ★ 94
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-skill safe to install? View the security audit →
Lightpanda Skill for LLM Agents A skill that provides integration with Lightpanda, a fast headless browser optimized for data extraction and web automation. What is this? This is a generalist skill for LLM agents (Claude Code, Openclaw, and others) that teaches agents how to use Lightpanda as a drop-in replacement for Chrome/Chromium when performing web scraping and automation tasks. Features Faster and lighter than Chrome for headless operations (9x faster, 16x less memory) Native MCP server with agent-optimized tools CLI fetch command with wait strategies and multiple output formats CDP (Chrome DevTools Protocol) compatible with custom LP domain extensions Works with Playwright and Puppeteer JavaScript execution support Semantic tree and markdown extraction Installation Copy to your agent's skills directory, then run the install script to download the Lightpanda binary: Quick Setup for Claude Code (MCP) Three Ways to Use Lightpanda Platform
| Stars | 94 |
| Forks | 10 |
| Language | Shell |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 63.6418396758166/100 |
| Open Issues | 3 |
| Last Updated | 2026-08-28 |
| Created | 2026-02-05 |
| Platforms | browser, cli |
| Est. Tokens | ~7k |
These tools work well together with agent-skill for enhanced workflows:
Explore other popular codex skill tools:
agent-skill is Lightpanda browser skill for openclaw. It is categorized as a Codex Skill with 94 GitHub stars.
agent-skill is primarily written in Shell.
You can find installation instructions and usage details in the agent-skill GitHub repository at github.com/lightpanda-io/agent-skill. The project has 94 stars and 10 forks, indicating an active community.
agent-skill is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: