Versioned security assessment

Report ID: SA-61E95843

6/30/2026, 1:19:47 AM

firecrawl-agent security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
firecrawl-agent
Version
v2
Maintainer
firecrawl
Source
github.com/firecrawl/cli/tree/main/skills/firecrawl-agent/
Coverage
1 Files scanned · 58 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

2 confirmed security findings require attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Static findings for markdown backticks, relative documentation links, and weak cryptography are false positives. The real risk is legitimate but elevated: the skill grants wildcard Firecrawl CLI execution, performs network extraction, and supports file output paths.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 58 Lines analyzed

3 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 3 evidence locations

Filesystem access

May read or write local files.

Observed in 2 evidence locations

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 2 evidence locations

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:6-7
Wildcard Firecrawl CLI Execution
The allowed-tools block permits Bash(firecrawl *) and Bash(npx firecrawl *). This is needed for the skill, but wildcard command arguments increase impact if prompts or parameters are abused.
The Bash allowlist is explicit and uses wildcard arguments. The intent appears legitimate because all examples use the Firecrawl CLI for the documented extraction workflow.
RISK-002 Medium
SKILL.md:4SKILL.md:12SKILL.md:24-30
External Network Extraction By Design
The skill instructs the agent to navigate websites and run Firecrawl Agent commands. User goals, URLs, schemas, and extracted page data may be processed through an external service.
The documented purpose is autonomous website extraction. This is not malicious, but it creates clear privacy and compliance considerations for target URLs and extracted data.
Needs review findings (1)
REVIEW-001 Low
SKILL.md:24-30SKILL.md:40-44
Output And Schema File Path Handling
The documented CLI options allow schema files and output paths. These are normal Firecrawl features, but users should avoid sensitive paths and review generated files before sharing.
The file path options are visible in examples and the options table. No evidence shows forced overwrite, unauthorized reads, or malicious path construction.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Static false positives ignored (3)
Low
SKILL.md:22SKILL.md:31SKILL.md:37-44SKILL.md:48-50
Markdown Backtick Static Findings Are False Positives
The Ruby or shell backtick findings point to markdown code fences, inline option formatting, and tips. They do not show Ruby execution or shell substitution.
The cited lines are markdown syntax or inline code labels. They are documentation text, not executable Ruby or shell backtick expressions.
Low
SKILL.md:55-57
Relative Documentation Links Are False Positives
The path traversal findings are relative markdown links to neighboring Firecrawl skill documents. They are not file access logic and do not traverse user files at runtime.
The cited lines are documentation links under the See also section. No runtime filesystem operation or user-controlled path resolution is present.
Low
SKILL.md:3-4SKILL.md:35
Weak Cryptography Findings Are False Positives
The cited lines do not contain cryptographic functions, hashes, ciphers, or password handling. No evidence found for weak cryptographic algorithm usage.
The cited locations are frontmatter description text and a markdown table header. There is no cryptographic implementation in the reviewed file.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable