Web Scraper
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only web-scraper is aligned with its stated purpose, but users should keep crawling, rate, proxy, and user-agent settings within site rules and the law.
Install only if you intend to use it for permitted web scraping. Keep rates low, bound crawl depth, avoid restricted or private content, and follow each website's robots.txt, terms, and applicable law.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
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.
A user could unintentionally overload a website, violate terms of service, or collect data inappropriately if they run broad crawls or use proxy/user-agent features to avoid restrictions.
The skill explicitly supports crawling and scraper controls that are normal for this purpose but could be misused to create excessive traffic or bypass site preferences if the user configures them irresponsibly.
`crawl [website] depth [n]` ... `Proxy support` ... `User agent rotation` ... `Default: 1 request/second`
Use only on sites where scraping is permitted, respect robots.txt and terms of service, keep crawl depth and request rate conservative, and do not use proxies or user-agent rotation to evade blocks.