Versioned security assessment

Report ID: SA-62E2A730

7/5/2026, 8:37:24 PM

mcp-builder security assessment v3

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
mcp-builder
Version
v3
Maintainer
mcp-use
Source
github.com/mcp-use/mcp-use/tree/main/skills/mcp-builder/
Coverage
12 Files scanned · 1,666 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

1 confirmed security finding requires 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 are false positives from Markdown examples, TypeScript template literals, placeholder environment variables, and sample URLs. No prompt injection or malicious exfiltration intent was found. The main risk is the deprecated skill telling agents to install a replacement with npx without explicit confirmation.

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

12 Files scanned · 1,666 Lines analyzed

1 item 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 5 evidence locations

Filesystem access

May read or write local files.

Not recorded by this audit

Env variables

May read values from the process environment.

Observed in 10 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 37 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:4-7
Agent-Directed Replacement Skill Installation
SKILL.md deprecates this skill and instructs the agent to install mcp-app-builder with npx if it is missing. This can trigger network package execution and skill installation outside the user's immediate request, so it should require explicit user confirmation.
The install instruction is explicit and appears in the activation description, so agents may treat it as workflow guidance. It points to a same-repository replacement and is not disguised as a system override, so severity is medium.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    Deprecated skill instructs agents to install a replacement skill with npx.
    Replace the automatic install directive with migration guidance that asks for user confirmation before any command runs.
  2. FIX-002
    Low
    Example API authentication places an API key in a URL query string.
    Prefer header-based authentication in examples, or warn that URLs with secrets can be logged by clients and proxies.
  3. FIX-003
    Low
    Documentation examples trigger command and secret pattern scanners.
    Label examples as illustrative, keep command snippets out of activation text, and avoid shell-like commands in frontmatter.

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.

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