browser-auto-download
Security checks across malware telemetry and agentic risk
Overview
This skill is purpose-aligned for browser-based downloads, but users should only run it on trusted download pages because it can automatically navigate, click, and save files.
This skill appears aligned with its stated purpose. Before installing, understand that it can open webpages, follow download-related links, click buttons, and save files to your Downloads folder. Use it only on trusted sites, verify any downloaded installer before running it, and avoid debug mode on sensitive pages unless you plan to delete the saved debug files afterward.
VirusTotal
64/64 vendors flagged this skill as clean.
Risk analysis
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 on an untrusted or unintended site, the agent may download the wrong file or an unsafe installer, although the artifacts do not show that it executes downloaded files.
The skill is explicitly designed to automate browser navigation and clicking to trigger downloads. This is coherent with its purpose, but it gives the agent broad download automation capability for user-supplied pages.
The script will: 1. Check for auto-downloads on page load 2. Look for platform-specific page links (PC/Desktop version) 3. Navigate if needed 4. Try clicking download buttons as fallback
Use it only with trusted download pages, review the downloaded filename and source, and avoid running downloaded executables without separate verification.
Users may need to install extra packages and a browser runtime manually, which introduces normal dependency provenance considerations.
The skill requires external Playwright and Chromium installation steps, while the registry reports no install spec. This is expected for browser automation, but dependency setup is not captured by the registry install contract.
pip install playwright playwright install chromium
Install dependencies from official package sources and verify the Playwright/Chromium installation before using the skill.
If debug mode is used on a page containing private or sensitive information, copies of that page content may remain in the Downloads debug folder.
Debug mode can persist screenshots, full HTML, and extracted page text to local files. This is disclosed troubleshooting behavior, but it can retain page content after the task.
debug_dir = os.path.join(output_dir, "browser-auto-download-debug") ... page.screenshot(path=screenshot_path) ... f.write(html_content) ... f.write(text_content)
Use debug mode only when needed and delete the generated debug folder after troubleshooting, especially for non-public pages.