📦
firecrawl-build-scrape
82Build Firecrawl Single-Page Scraping
Apps often need clean content from one known URL. This skill guides a focused Firecrawl /scrape integration for page extraction.
Coding & Development View
Skills firecrawl-agent
📦
firecrawl-agent
Content revision r1 Medium Risk ⚙️ External commands📁 Filesystem access
Extract Website Data with Firecrawl Agent
Complex websites often require multi-page navigation before data can be collected. This skill guides Claude, Codex, or Claude Code to run Firecrawl Agent and return structured website data.
Supports: Claude Codex Code(CC)
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-agent" from https://skillstore.io/skills/firecrawl-firecrawl-agent.md and its manifest at https://skillstore.io/api/skills/firecrawl-firecrawl-agent/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-agent". Extract pricing from a SaaS pricing page.
Expected outcome:
A structured pricing summary with plan names, monthly prices, annual discounts, feature limits, and source URLs.
Using "firecrawl-agent". Get products from an ecommerce category.
Expected outcome:
A product table covering item name, price, availability, product link, and fields that could not be verified.
Using "firecrawl-agent". Collect directory entries from multiple starting pages.
Expected outcome:
A deduplicated list of directory records with organization names, categories, locations, profile links, and source pages.
Security Audit
Medium Riskv4 • 7/5/2026 Open versioned report
The static findings are false positives caused by Markdown code fences, inline option names, and sibling documentation links. No prompt injection, credential access, or hidden data-exfiltration instructions were found in the reviewed skill file. A separate semantic concern remains because the skill allows runtime execution through npx firecrawl.
1
Files scanned
58
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (1)
Medium
Runtime Package Execution via npx
The skill allows Bash permission for npx firecrawl commands. Running npx can execute package code resolved outside the reviewed skill file, which increases supply-chain and runtime command risk.
The allowed-tools block explicitly includes Bash(npx firecrawl *). This is a real execution capability, but the command prefix is limited to Firecrawl.
Risk Factors
⚙️ External commands (13)
📁 Filesystem access (3)
Audited by: codex View Audit History →
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.
Copy report link
https://skillstore.io/skills/firecrawl-firecrawl-agent/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/firecrawl-firecrawl-agent?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/firecrawl-firecrawl-agent?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/firecrawl-firecrawl-agent/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/firecrawl-firecrawl-agent.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 · BibTeX · CFF)
APA citation
firecrawl. (2026). firecrawl-agent security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/firecrawl-firecrawl-agent/audits/4BibTeX citation
@techreport{firecrawl-firecrawl-firecrawl-agent-2026,
author = {firecrawl},
title = {firecrawl-agent security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/firecrawl-firecrawl-agent/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-agent 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-agent/audits/4"
identifiers:
- type: other
value: "skillstore:firecrawl-firecrawl-agent:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance
What You Can Build
SaaS Pricing Research
Collect plan names, prices, feature limits, and source URLs from complex pricing pages.
Catalog Monitoring
Extract product names, prices, availability, and links from category pages that require navigation.
Directory Data Collection
Build structured lists of organizations, locations, categories, and profile links from public directories.
Try These Prompts
Basic Pricing Extraction
Use Firecrawl Agent to extract pricing tiers from [site URL]. Wait for completion and save the structured result under .firecrawl/pricing.json.
Product Catalog Extraction
Extract product names, prices, availability, and product URLs from [catalog URL]. Use a schema and return only verified fields.
Directory Extraction with Limits
Extract organization names, categories, locations, contact pages, and source URLs from [directory URL]. Set a credit limit of [number].
Schema File Extraction Workflow
Use my workspace schema file at [path] to extract nested plan, feature, and limitation data from [site URL]. Save results under .firecrawl.
Best Practices
- Keep output files inside a dedicated .firecrawl directory.
- Use schemas when you need predictable fields and easier validation.
- Set credit limits before running broad or uncertain extractions.
Avoid
- Do not use the agent for a single simple page when a scrape is enough.
- Do not extract private, paywalled, or restricted data without authorization.
- Do not pass unreviewed shell text, unsafe paths, or secret values into commands.
Frequently Asked Questions
What does this skill do?
It guides Firecrawl Agent to navigate websites and extract structured data for Claude, Codex, and Claude Code workflows.
Does it scrape pages directly inside the model?
No. It guides an approved Firecrawl CLI command, and Firecrawl performs the navigation and extraction.
When should I use it instead of simple scraping?
Use it when the target data spans multiple pages or requires the agent to discover where the data appears.
Can it use a schema?
Yes. It supports inline schemas and schema files for predictable structured output.
Where are results saved?
The examples save results under .firecrawl, and users should keep outputs in that workspace area.
What should I check before running it?
Confirm authorization for the target site, set a credit limit, and review paths before saving output.
Developer Details
Author
firecrawlLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
30c73eac2afe762f6aa9c4553158769369d47351
Maintenance freshness
7/18/2026
Usage
3 downloads · 88 views
File structure
📄 SKILL.md
More from firecrawl
View all📦
firecrawl-build-interact
82Build Firecrawl Browser Interactions
Dynamic pages often hide data behind clicks, forms, and login flows. This skill helps teams choose and scope Firecrawl /interact integrations.
Coding & Development View
📦
firecrawl-build-search
81Build Firecrawl Search Workflows
Teams need reliable source discovery before scraping or answering questions. This skill guides Firecrawl search integration, result selection, and follow-up extraction decisions.
Coding & Development View
📦
firecrawl-search
78Search the Web with Firecrawl
Current web research often needs more than short search snippets. This skill runs Firecrawl searches, saves structured results, and can extract full page content for review.
Research & Learning View
📦
firecrawl-crawl
78Crawl Websites with Firecrawl
Teams need reliable content from many pages without manual copying. This skill guides Firecrawl crawls with scoped paths, limits, progress, and saved results.
Data & Analytics View
📦
firecrawl-scrape
77Scrape Web Pages Into Clean Markdown
Web pages can be hard to extract cleanly when scripts render important content. This skill uses Firecrawl to scrape URLs into LLM-ready markdown and optional formats.
Research & Learning View
Related Skills
View all📦
lark-doc
87Manage Lark Docs and Feishu Wiki Content
by larksuite
Teams need reliable document updates without switching between tools. This skill guides Claude, Codex, and Claude Code through authenticated lark-cli workflows for Lark Docs.
Office & Reports View
📦
pptx
85Create PowerPoint Presentations with Python
by AutumnsGrove
Building polished PowerPoint decks by hand is slow and hard to repeat. This skill guides Claude, Codex, and Claude Code through PPTX creation, editing, and automation with python-pptx.
Office & Reports View
📦
building-agents
85Build Claude Code Agents
by C0ntr0lledCha0s
Creating reliable AI agents requires clear schemas, safe tools, and repeatable review steps. This skill guides agent design, validation, migration, and maintenance for Claude Code workflows.
Coding & Development View
📦
building-commands
84Build Claude Code Slash Commands
by C0ntr0lledCha0s
Teams need repeatable AI workflows that are easy to invoke and review. This skill helps create, update, validate, and document Claude Code slash commands.
Coding & Development View
📦
creating-issues
84Create Consistent GitHub Issues
by C0ntr0lledCha0s
Poorly structured issues create ambiguity and require manual cleanup. This skill drafts and validates titles, bodies, labels, milestones, projects, and relationships.
Coding & Development View
📦
building-plugins
83Build Claude Code Plugins
by C0ntr0lledCha0s
Creating Claude Code plugins requires correct structure, validation, documentation, and safe packaging. This skill guides users through plugin architecture, templates, validation, and publishing workflows.
DevOps & Infrastructure View