Skip to content
skillsafebeta
← Report library
Purpose / Data analysis

Firecrawl Seo Audit Skill Security Audit

What the author says it does (original text)

Audit a website's SEO with Firecrawl. Use when the user asks for an SEO audit, metadata and heading review, sitemap/site-structure analysis, keyword opportunities, competitor SERP comparison, or prioritized search optimization recommendations.

Independent security check

Security risks found

Files checked
1
Risks found
3
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.No risks found
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.Risks found: 1
Medium risk

Hosted crawling discloses target URLs and may process page content through Firecrawl

Source references: 3
What we found

The workflow explicitly uses hosted Firecrawl requests to map and scrape a site. The service must at least receive the target URLs and retrieve page content; non-public URLs, sensitive paths, or URLs containing access tokens would therefore be processed by a third party.

Why this matters

Sensitive URLs, site structure, or page content may enter Firecrawl's processing scope. The resulting report also records scraped URLs, the site, and keywords.

The Skill explicitly uses hosted Firecrawl requests to map a target site and scrape pages, so the third party will process the target URLs and requested page content. If a user supplies private addresses, token-bearing URLs, or sensitive paths, those details may be disclosed. Users can ask about Firecrawl's retention policy and restrict targets to public, authorized URLs without embedded credentials.

SKILL.md:11In the instructionsOpen original file
inputs:  - name: FIRECRAWL_API_KEY    description: Firecrawl API key for hosted Firecrawl requests.    required: true---
Show 2 other places
SKILL.md:28In the instructionsOpen original file
1. Map the site with Firecrawl to understand URL structure.2. Scrape key pages: homepage, product/service pages, pricing, docs, blog, about, and high-value landing pages.3. Extract title tags, meta descriptions, headings, internal links, content structure, canonical signals when visible, and image alt text when available.4. Search target keywords when provided; scrape top ranking pages for comparison.
SKILL.md:65In the instructionsOpen original file
## Sources[URLs scraped and what was checked]## Rerun Inputsworkflow: firecrawl-seo-auditsite: [url]keywords: [list]output: [markdown/json]
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.No risks found
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.Risks found: 1
Medium risk

Scraped web content may inject instructions into the auditing agent

Source references: 2
What we found

The Skill directs the agent to scrape both the audited site and ranking competitor pages and use them for specific recommendations, but the visible instructions do not require commands, prompts, or fake system messages in those pages to be treated solely as untrusted data. Malicious page text could therefore influence later reasoning.

Why this matters

In an implementation that exposes raw scraped text to an action-capable model, a page author could try to divert the audit, elicit contextual information, or manipulate conclusions. The supplied text does not show that such an event has occurred.

What this evidence establishes

The Skill scrapes the site and competitor pages and uses findings in its audit, but the supplied source does not show how scraped results reach the model or that commands found in pages will be executed. The risk depends on a malicious page being treated as instructions; the visible text only establishes that no explicit untrusted-content boundary is stated. Users can require page text to be treated solely as data and constrain subsequent tool calls.

This assessment concerns the code and conditions shown, not proof that harm has occurred.
SKILL.md:29In the instructionsOpen original file
1. Map the site with Firecrawl to understand URL structure.2. Scrape key pages: homepage, product/service pages, pricing, docs, blog, about, and high-value landing pages.3. Extract title tags, meta descriptions, headings, internal links, content structure, canonical signals when visible, and image alt text when available.4. Search target keywords when provided; scrape top ranking pages for comparison.
Show 1 other places
SKILL.md:77In the instructionsOpen original file
- Make recommendations specific, not generic.- Show the page or source behind each issue.- Distinguish technical findings from content strategy guesses.
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.Risks found: 1
Medium risk

Unbounded crawling and keyword comparison may consume substantial Firecrawl quota

Source references: 1
What we found

The workflow maps the site, scrapes several classes of important pages, and scrapes ranking pages for supplied keywords, but sets no URL, keyword, crawl-depth, or request budget. Large sites or long keyword lists can expand hosted request volume.

Why this matters

The user's Firecrawl quota could be consumed quickly, potentially causing extra charges under the account's billing terms or leaving insufficient quota for other work.

These are legitimate SEO-audit operations, but the instructions call for site mapping, several classes of page scraping, and ranking-page scraping for supplied keywords. No URL, keyword, depth, or request-budget limit is visible. A large site or long keyword list could therefore increase hosted-request usage and cost. Users can require explicit page, keyword, and spending caps before a run.

SKILL.md:28In the instructionsOpen original file
1. Map the site with Firecrawl to understand URL structure.2. Scrape key pages: homepage, product/service pages, pricing, docs, blog, about, and high-value landing pages.3. Extract title tags, meta descriptions, headings, internal links, content structure, canonical signals when visible, and image alt text when available.4. Search target keywords when provided; scrape top ranking pages for comparison.

Inside this skill

5 instruction sections

The Skill's workflow matches its stated SEO-audit purpose: it maps the site, scrapes important pages, extracts SEO elements, and may search keywords and scrape ranking pages for comparison.

View source
SKILL.md:28In the instructionsOpen original file
1. Map the site with Firecrawl to understand URL structure.2. Scrape key pages: homepage, product/service pages, pricing, docs, blog, about, and high-value landing pages.3. Extract title tags, meta descriptions, headings, internal links, content structure, canonical signals when visible, and image alt text when available.4. Search target keywords when provided; scrape top ranking pages for comparison.

The Skill requires a Firecrawl API key for hosted Firecrawl requests. The visible content does not instruct the agent to write that key into files, logs, or reports.

View source
SKILL.md:10In the instructionsOpen original file
  source: https://github.com/firecrawl/firecrawl-workflowsinputs:  - name: FIRECRAWL_API_KEY    description: Firecrawl API key for hosted Firecrawl requests.    required: true---

The final report is instructed to list scraped URLs and checked material, and to record the site and keywords for reruns. This can preserve the audit scope in the output, but the template does not request the API key.

View source
SKILL.md:65In the instructionsOpen original file
## Sources[URLs scraped and what was checked]## Rerun Inputsworkflow: firecrawl-seo-auditsite: [url]keywords: [list]output: [markdown/json]```
Start here · InstructionsSKILL.md
firecrawl-seo-audit
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source.
Files and check records1 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions

Operations mentioned in code and instructions

Connect to websites
SKILL.md:8In the instructionsOpen original file
  version: "0.1.0"  homepage: https://www.firecrawl.dev  source: https://github.com/firecrawl/firecrawl-workflows
SKILL.md:9In the instructionsOpen original file
  homepage: https://www.firecrawl.dev  source: https://github.com/firecrawl/firecrawl-workflowsinputs:
SKILL.md:12In the instructionsOpen original file
  - name: FIRECRAWL_API_KEY    description: Firecrawl API key for hosted Firecrawl requests.    required: true
Read keys or account settings
SKILL.md:11In the instructionsOpen original file
inputs:  - name: FIRECRAWL_API_KEY    description: Firecrawl API key for hosted Firecrawl requests.
Lines read
80
File checksum (to compare versions)
9dab4e6f0805028404f148754ffb784357a838e79042aede4cc1b72161c56fd9