Skip to content
skillsafebeta
← Report library
Purpose / Other

Firecrawl Deep Research Skill Security Audit

What the author says it does (original text)

|

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

Research queries are sent to the hosted Firecrawl service

Source references: 2
What we found

The skill requires Firecrawl search and scraping and explicitly requires an API key for hosted requests. Execution therefore sends research topics, query terms, and target URLs to a third-party service. The instructions do not require confidential, contract-restricted, or personally identifiable information to be removed first.

Why this matters

If a topic or query contains an unreleased project, customer name, health information, or internal investigation clue, the third-party service may receive and log it.

The skill explicitly requires an API key for hosted Firecrawl requests and directs the agent to perform Firecrawl searches and scrapes. When the hosted service is used, research queries and scrape targets leave the user's environment; the source does not require screening or removing confidential, personal, or contract-restricted information first. The risk depends on the user's input and the tool surface actually used. Users can ask what fields are transmitted and retained, and restrict sensitive topics, queries, or private URLs.

SKILL.md:25In 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---
Show 1 other places
SKILL.md:62In the instructionsOpen original file
Use Firecrawl search and scrape through the CLI or equivalent tool surface. Matchdepth to the runtime the user chose during onboarding.
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

The Exhaustive tier has no request ceiling and can create open-ended API usage

Source references: 2
What we found

“Longer / no limit” maps to Exhaustive, which specifies at least 10 searches and at least 25 scraped sources but sets no maximum request count, budget, or stopping threshold.

Why this matters

On a metered or quota-limited Firecrawl account, prolonged research could consume an unpredictable amount of quota or incur charges.

The skill maps “longer / no limit” to Exhaustive and specifies only lower bounds of 10+ searches and 25+ scraped sources, with no maximum call count, cost budget, or explicit stopping condition. This does not prove calls will continue indefinitely, but it permits open-ended hosted API usage when a user selects “no limit,” potentially increasing charges and external data transfer. Users can require hard limits on queries, scrapes, time, or cost before execution.

SKILL.md:51In the instructionsOpen original file
Map the answer to a depth tier in the Collection Plan below:- A few minutes → Quick- ~10-15 minutes → Thorough- Longer / no limit → Exhaustive
Show 1 other places
SKILL.md:65In the instructionsOpen original file
- Quick (~a few minutes): search 3-5 queries and scrape 5-10 high-quality sources.- Thorough (~10-15 minutes): search 5-10 queries from different angles and scrape 15-25 sources.- Exhaustive (longer): search 10+ queries and scrape 25+ sources, including primary sources, research papers, expert views, and contrarian sources.

Inside this skill

5 instruction sections

The skill is limited to formal deep-research reports explicitly requested by the user and excludes product recommendations, ranked lists, and quick lookups.

View source
SKILL.md:33In the instructionsOpen original file
Use this only for report-scale research: a rigorous, cited synthesis the userexplicitly wants delivered as a formal written report. If the request is aproduct pick, a top-N list, a quick lookup, or anything answerable with a shortsearch, stop; do not use this skill, let the request be handled the standardway.

Before starting, the skill asks for a runtime and maps it to Quick, Thorough, or Exhaustive collection depth.

View source
SKILL.md:47In the instructionsOpen original file
Infer the topic and output format from context. Before starting, unless already specified, always ask one short question to define the scope:> "How long do you want this research task to run?"Map the answer to a depth tier in the Collection Plan below:- A few minutes → Quick- ~10-15 minutes → Thorough- Longer / no limit → Exhaustive

Research uses Firecrawl to search and scrape the open web, with the selected depth controlling the number of queries and sources.

View source
SKILL.md:62In the instructionsOpen original file
Use Firecrawl search and scrape through the CLI or equivalent tool surface. Matchdepth to the runtime the user chose during onboarding.- Quick (~a few minutes): search 3-5 queries and scrape 5-10 high-quality sources.- Thorough (~10-15 minutes): search 5-10 queries from different angles and scrape 15-25 sources.- Exhaustive (longer): search 10+ queries and scrape 25+ sources, including primary sources, research papers, expert views, and contrarian sources.

The final report is required to cite factual claims, prefer primary sources, and disclose uncertainty and conflicting evidence.

View source
SKILL.md:139In the instructionsOpen original file
## Quality Bar- Cite sources for factual claims.- Prefer primary sources when available.- Flag uncertainty and conflicting evidence.- Synthesize instead of listing scrape summaries.
Start here · InstructionsSKILL.md
firecrawl-deep-research
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:23In the instructionsOpen original file
  version: "0.1.0"  homepage: https://www.firecrawl.dev  source: https://github.com/firecrawl/firecrawl-workflows
SKILL.md:24In the instructionsOpen original file
  homepage: https://www.firecrawl.dev  source: https://github.com/firecrawl/firecrawl-workflowsinputs:
SKILL.md:27In 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:26In the instructionsOpen original file
inputs:  - name: FIRECRAWL_API_KEY    description: Firecrawl API key for hosted Firecrawl requests.
Lines read
145
File checksum (to compare versions)
ba7deee7214c41706e58429571a83be620582d2057c447ff2b167386baf6aa23