Novel Scraper SPA
PassAudited by ClawScan on May 10, 2026.
Overview
This skill is a coherent novel-scraping utility, with the main cautions being normal browser/network scraping behavior and undeclared Python/Playwright dependencies.
This appears safe for its advertised purpose. Before installing, be aware that it needs external Python packages/Playwright despite no install spec, and only ask it to scrape URLs and write files in locations you approve.
Findings (2)
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.
The target website will receive requests from the user's environment, JavaScript may run in a fresh headless browser, and scraped text will be saved locally.
The tool fetches/renders a supplied URL and writes extracted content to disk. This is expected for a scraper, but it means the agent should be directed to scrape only intended sites and write only to approved locations.
response = requests.get(url, timeout=30) ... html = get_html(url) ... with open(output_file, "w", encoding="utf-8") as f:
Use the skill only for URLs you intend to scrape, avoid private/internal network targets unless explicitly desired, and keep output paths scoped to the workspace unless you intentionally choose another file.
The skill may fail until dependencies are installed, and any manual dependency installation should be done from trusted package sources.
The code depends on Playwright, while the registry/install information provides no install spec or pinned dependency list. This is a provenance and reproducibility note, not evidence of malicious behavior.
from playwright.sync_api import ( sync_playwright, Page, TimeoutError as PlaywrightTimeout, Playwright, )
Add a requirements/install specification with pinned or minimum-safe versions for Playwright, requests, BeautifulSoup, and any required browser setup.