Skills firecrawl-download
๐Ÿ“ฆ

firecrawl-download

Content revision r1 Medium Risk โš™๏ธ External commands๐ŸŒ Network access๐Ÿ“ Filesystem access

Download Websites for Offline Reference

Saving documentation by hand is slow and easy to miss. This skill uses Firecrawl to map pages, download selected content, and organize local files.

Supports: Claude Codex Code(CC)
๐Ÿ“Š 70 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "firecrawl-download" from https://skillstore.io/skills/firecrawl-firecrawl-download.md and its manifest at https://skillstore.io/api/skills/firecrawl-firecrawl-download/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "firecrawl-download". Download the product docs for offline review.

Expected outcome:

A local .firecrawl folder contains organized Markdown pages and a short summary of the downloaded documentation URLs.

Using "firecrawl-download". Capture guide pages with screenshots.

Expected outcome:

Each saved guide page includes readable content and a screenshot, grouped by the site path.

Using "firecrawl-download". Archive only API pages and skip translations.

Expected outcome:

Only matching API pages are saved, translated sections are excluded, and the run reports page counts.

Security Audit

Medium Risk
v4 โ€ข 7/5/2026 Open versioned report

Most static findings are false positives from Markdown backticks, example.com URLs, and relative documentation links. The remaining risks are contextual: the skill permits unpinned npx execution and encourages skipping confirmation for bulk downloads.

1
Files scanned
70
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (2)

Medium
Unpinned NPX Command Execution
The skill allows Bash(npx firecrawl *), which can resolve and execute an npm package at runtime. This creates supply-chain and version drift risk for a network and filesystem tool.
The allowed-tools entry explicitly permits npx firecrawl commands, and no package version pin is shown. The risk depends on installer behavior, so confidence is high but not absolute.
Medium
Automated Confirmation Bypass
The skill tells agents to always pass -y and says to use it in automated flows. This removes a confirmation safeguard before bulk downloads and local file writes.
The text directly instructs use of -y to skip confirmation. The skill also downloads many pages to disk, so the operational impact is clear.
Audited by: codex View Audit History โ†’
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/firecrawl-firecrawl-download/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/firecrawl-firecrawl-download/security.svg)](https://skillstore.io/skills/firecrawl-firecrawl-download?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/firecrawl-firecrawl-download?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/firecrawl-firecrawl-download/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/firecrawl-firecrawl-download.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA ยท BibTeX ยท CFF)

APA citation

firecrawl. (2026). firecrawl-download security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/firecrawl-firecrawl-download/audits/4

BibTeX citation

@techreport{firecrawl-firecrawl-firecrawl-download-2026, author = {firecrawl}, title = {firecrawl-download security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/firecrawl-firecrawl-download/audits/4}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "firecrawl-download security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "firecrawl" date-released: "2026-07-05" url: "https://skillstore.io/skills/firecrawl-firecrawl-download/audits/4" identifiers: - type: other value: "skillstore:firecrawl-firecrawl-download:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
91
Spec Compliance

What You Can Build

Build Offline Documentation Sets

Download product or API docs as local Markdown files for review without constant network access.

Archive Web Research Sources

Save selected pages, links, and screenshots from a source site for later analysis.

Capture Site Sections for QA

Download specific paths with screenshots to compare content, links, and page structure.

Try These Prompts

Download a Small Documentation Site
Download [URL] as Markdown for offline reading. Limit the run to 20 pages and ask before any larger download.
Save Pages With Screenshots
Download [URL] with Markdown and screenshots. Include only the docs section and keep the saved files organized.
Filter a Site Archive
Download [URL] with Markdown and links. Include /guides and /api, exclude translated paths, and set a practical page limit.
Prepare a Review Snapshot
Create a local review snapshot of [URL]. Save main content, links, and screenshots, then summarize what was downloaded and skipped.

Best Practices

  • Set page limits and include paths before downloading large sites.
  • Confirm that the target site allows automated downloading.
  • Review saved files before sharing, indexing, or committing them.

Avoid

  • Running unrestricted downloads against an entire production domain.
  • Using -y in automation without a clear allowlist and page limit.
  • Downloading authenticated or private pages into shared folders.

Frequently Asked Questions

What does this skill download?
It downloads discovered pages from a target site as local files, such as Markdown, links, and screenshots.
Where are the files saved?
The skill describes saving output under a local .firecrawl directory with nested folders by page.
Can it limit the download scope?
Yes. It supports limits, search filters, include paths, exclude paths, and subdomain control.
Can it capture screenshots?
Yes. The documented options include standard screenshots and full page screenshots.
Does it require Firecrawl?
Yes. It requires access to the Firecrawl CLI and any credentials or configuration needed by that tool.
Is it safe for private websites?
Use caution. Confirm permission first, limit the scope, and keep downloaded private content out of shared folders.

Developer Details

Author

firecrawl

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Ref

30c73eac2afe762f6aa9c4553158769369d47351

Maintenance freshness

7/20/2026

Usage

4 downloads ยท 108 views

File structure

๐Ÿ“„ SKILL.md