agent-browser

skills-101/superpowers

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

59,813次安裝

第 409 位，共 500 · 前 81.8%

於 Top 500 安裝量曲線上的位置（對數刻度） · 數據截至 2026-08-24

安全審計

MEDIUM

The agent-browser skill provides browser automation via the belt CLI, allowing agents to navigate, interact with, and extract data from websites. Key security considerations include the ability to execute arbitrary JavaScript on pages and the automation of login sequences. While the skill provides guidance on secure credential management, its capability to run code and its exposure to untrusted web content (indirect prompt injection) represent elevated security surfaces.

審計方 Gen Agent Trust Hub · 2026-08-08 · warn

查看原始出處在 skills.sh 查看

MARKET SIGNALS · SKILL INDEX