Skip to content
skillsafebeta
← Report library
Purpose / Documents

Firecrawl Knowledge Ingest Skill Security Audit

What the author says it does (original text)

Ingest public or authenticated knowledge bases and docs portals with Firecrawl browser. Use for JS-heavy docs, login-gated portals, paginated help centers, support knowledge bases, or structured JSON/markdown extraction from documentation sites.

Independent security check

Security risks found

Files checked
1
Risks found
2
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

Login-gated portal content may be processed by hosted Firecrawl

Source references: 6
What we found

The Skill requires an API key for “hosted Firecrawl requests” and explicitly directs the Firecrawl browser to collect authenticated portal content and metadata. Although it says to respect authentication boundaries, it does not state whether portal content, session data, or login material is sent to Firecrawl, how it is retained, or who can access it.

Why this matters

When used on internal documentation, customer-support knowledge bases, or other private portals, restricted articles and metadata may enter a third-party processing environment subject to that service's retention, access-control, regional, and logging policies.

The Skill explicitly targets login-gated portals, requires an API key for hosted Firecrawl requests, and directs the Firecrawl browser to collect article content and metadata. If the user authorizes access to an authenticated portal, restricted material may therefore be processed by a third-party hosted service. “Respect authentication boundaries” does not explain how sessions or content are transmitted or retained. Users can request data-flow and retention details and restrict the account, pages, and sensitive material exposed.

SKILL.md:11In the instructionsOpen original file
inputs:  - name: FIRECRAWL_API_KEY    description: Firecrawl API key for hosted Firecrawl requests.    required: true---
Show 5 other places
SKILL.md:28In the instructionsOpen original file
Use Firecrawl browser to:- open the portal and inspect navigation- identify sections, categories, sidebar links, and article URLs- follow sidebar navigation, next links, pagination, load-more controls, or search- scrape article content as markdown- extract metadata such as title, section, last updated date, author, and tags
SKILL.md:36In the instructionsOpen original file
Try Firecrawl map as a supplement for public URLs, but use browser navigation for auth-gated or JS-heavy content.
SKILL.md:74In the instructionsOpen original file
- Track extraction progress and page failures.- Respect authentication boundaries.
SKILL.md:3In the instructionsOpen original file
name: firecrawl-knowledge-ingestdescription: Ingest public or authenticated knowledge bases and docs portals with Firecrawl browser. Use for JS-heavy docs, login-gated portals, paginated help centers, support knowledge bases, or structured JSON/markdown extraction from documentation sites.license: ISC
SKILL.md:33In the instructionsOpen original file
- follow sidebar navigation, next links, pagination, load-more controls, or search- scrape article content as markdown- extract metadata such as title, section, last updated date, author, and tags
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.No risks found
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

Inferring the page limit and crawling immediately can expand scope and cost without confirmation

Source references: 3
What we found

The instructions say to infer the page limit from context and proceed immediately when the portal is clear, while also following sidebars, next links, pagination, load-more controls, and search. Without a reliable explicit cap, this can create a broad hosted-API job.

Why this matters

The user may consume more Firecrawl quota or incur more charges than expected, and the workflow may collect substantially more portal pages than intended. On authenticated portals, broad traversal also increases the volume of private material processed.

The Skill says to infer the page limit and proceed immediately when the portal is clear, while collection may expand through navigation, pagination, load-more controls, and search. If context lacks a firm limit, the resulting scope could exceed the user’s expectation and consume additional hosted API usage. The source gives no pricing or evidence of an unbounded loop, and the deliverable records max_pages, so this is conditional. Users can require an explicit page cap, domain/path allowlist, and spending limit before execution.

SKILL.md:22In the instructionsOpen original file
Infer the portal URL, output format, auth needs, and page limit from context. If the portal is clear, proceed immediately.Ask at most 1-3 concise questions only if blocked, such as the portal URL, whether authentication is required, or the desired output format.
Show 2 other places
SKILL.md:30In the instructionsOpen original file
- open the portal and inspect navigation- identify sections, categories, sidebar links, and article URLs- follow sidebar navigation, next links, pagination, load-more controls, or search- scrape article content as markdown- extract metadata such as title, section, last updated date, author, and tags
SKILL.md:58In the instructionsOpen original file
## Rerun Inputsworkflow: firecrawl-knowledge-ingesturl: [portal url]format: [json/markdown/merged]max_pages: [number]```

Inside this skill

5 instruction sections

This Skill is a collection-workflow instruction set with no accompanying executable script. It directs Firecrawl to browse portal navigation and pagination, extract article bodies as Markdown, and collect metadata such as titles, authors, and tags.

View source
SKILL.md:28In the instructionsOpen original file
Use Firecrawl browser to:- open the portal and inspect navigation- identify sections, categories, sidebar links, and article URLs- follow sidebar navigation, next links, pagination, load-more controls, or search- scrape article content as markdown- extract metadata such as title, section, last updated date, author, and tags

The workflow explicitly covers both public and login-gated knowledge bases. Public URLs may additionally use mapping, while authenticated or JavaScript-heavy content is handled through browser navigation.

View source
SKILL.md:3In the instructionsOpen original file
name: firecrawl-knowledge-ingestdescription: Ingest public or authenticated knowledge bases and docs portals with Firecrawl browser. Use for JS-heavy docs, login-gated portals, paginated help centers, support knowledge bases, or structured JSON/markdown extraction from documentation sites.license: ISC
SKILL.md:36In the instructionsOpen original file
Try Firecrawl map as a supplement for public URLs, but use browser navigation for auth-gated or JS-heavy content.

The intended output is JSON, Markdown, or a merged file containing source URLs, article content, metadata, failed-page information, and rerun parameters.

View source
SKILL.md:46In the instructionsOpen original file
## Output[JSON/markdown/merged file path or content]## Sections[Section names and article counts]## Failed Or Restricted Pages[Any access/loading issues]## Sources[URLs extracted]## Rerun Inputsworkflow: firecrawl-knowledge-ingesturl: [portal url]format: [json/markdown/merged]max_pages: [number]```
SKILL.md:65In the instructionsOpen original file
## JSON ShapeUse `source`, `url`, `extractedAt`, `totalArticles`, and `sections[]` with article `title`, `url`, `section`, `content`, and `metadata`.
Start here · InstructionsSKILL.md
firecrawl-knowledge-ingest
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
75
File checksum (to compare versions)
405e539ec883b2f676f2de074041bdf2bb468b2275ce5f9bbc22d48a23da9c14