Skylv Web Automation Bot
PassAudited by VirusTotal on May 4, 2026.
Overview
Type: OpenClaw Skill Name: skylv-web-automation-bot Version: 1.0.0 The skill bundle provides a legitimate and well-structured framework for browser automation using Playwright and Puppeteer, as described in SKILL.md and skill.json. It includes helper classes for intelligent element discovery, automated form filling, and web scraping, along with standard anti-detection techniques. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the code is entirely consistent with its stated purpose of UI automation.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If used carelessly, the agent could click buttons, fill forms, or capture page content on websites the user did not intend to affect.
The skill describes AI-planned browser actions that can navigate pages, click UI elements, enter text, save screenshots, and extract page content. This is expected for a browser automation skill, but it is broad enough to warrant user supervision.
for step in steps:\n self.execute_step(page, step) ... elif action == "goto" ... elif action == "click" ... elif action == "type" ... elif action == "screenshot" ... elif action == "extract"
Use it only for clearly specified websites and tasks, and require human confirmation before submitting forms, making purchases, deleting data, posting content, or taking other irreversible actions.
Users may need to trust and install external tooling such as Playwright or Puppeteer outside this package.
The package does not include executable code or an install script, which limits immediate supply-chain risk, but its provenance metadata is limited and the user would need to separately obtain any browser automation libraries.
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Verify the repository and any third-party packages before implementing the examples, and prefer pinned, well-reviewed dependencies.