Web Scraping

PassAudited by ClawScan on May 1, 2026.

Overview

This instruction-only web-scraping skill is coherent and not deceptive, but it can use browser sessions and save scraped results, so authenticated or private scraping should be scoped carefully.

This looks like a straightforward web-scraping helper. Before using it, define the target site, exact fields, and page limits; be especially careful with logged-in pages because the agent may access account-specific data and save extracted results to workspace files.

Findings (3)

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.

What this means

The agent may click, search, filter, paginate, or load many pages while collecting data.

Why it was flagged

The skill directs browser automation and page interaction, which is expected for dynamic web scraping but can still affect websites if used too broadly.

Skill content
Use `browser` when the site is dynamic, needs clicking, infinite scroll, filters, tabs, or login/session state.
Recommendation

Specify the exact site, fields, and page limits, and avoid large or aggressive scraping unless you have permission.

What this means

If used on a logged-in site, the agent could view and extract information available to that account.

Why it was flagged

The skill may rely on an authenticated browser session for login-gated sites. This is disclosed and purpose-aligned, but it can expose account-specific data.

Skill content
Use `browser` when the site is dynamic, needs clicking, infinite scroll, filters, tabs, or login/session state.
Recommendation

Use authenticated scraping only for accounts and pages you intend to access, and clearly state which fields should be collected.

What this means

Scraped information may remain in workspace files after the task completes.

Why it was flagged

The skill can persist scraped output or partial results in workspace files, which is useful for larger scraping tasks but may retain private or sensitive page data.

Skill content
Save results in the workspace when the task is larger than a quick one-off. ... For large jobs, checkpoint partial results to a workspace file.
Recommendation

Review saved outputs and delete or protect workspace files that contain private, account-specific, or sensitive data.