Versioned security assessment

Report ID: SA-26421118

7/9/2026, 3:39:00 PM

chatgpt-app-builder security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
chatgpt-app-builder
Version
v2
Maintainer
shubhamsaboo
Source
github.com/shubhamsaboo/awesome-llm-apps/tree/main/generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/chatgpt-app-builder
Coverage
18 Files scanned · 2,247 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.

Most static detections are false positives from documentation examples, JSX template literals, evaluation text, and placeholder CSP domains. I confirmed the replacement install flow in SKILL.md because it can trigger a networked npx install from community-authored instructions. No evidence found of credential exfiltration, malicious network calls, or prompt text that tries to alter this audit.

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

18 Files scanned · 2,247 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 15 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 1 evidence location

External commands

May invoke commands or programs outside the Skill.

Observed in 12 evidence locations

Capability review items (2)
Medium
SKILL.md:5
Ruby/shell backtick execution
Check if `mcp-app-builder` is available in the skills folder. If not, install it:
This line tells the agent to install a replacement skill if it is not available. In a community skill, that can trigger an unverified external install flow.
Medium
SKILL.md:6
Ruby/shell backtick execution
`npx skills install mcp-use/mcp-use --skill mcp-app-builder`
This line contains an npx skills install command, which can download and execute external package tooling. A community skill should not cause this without explicit user approval.

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:4-7
Unverified Replacement Skill Installation Redirect
SKILL.md lines 4-7 mark the skill as deprecated, tell the agent to install mcp-app-builder, and provide an npx skills install command. This can steer automated agents into a networked install from community-authored instructions without source pinning or explicit approval.
The redirect and installer command are explicit in the skill metadata block. The risk is supply-chain execution, not direct malware evidence.

Remediation

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

  1. FIX-001
    Medium
    The skill metadata directs agents to install a replacement skill with npx.
    Remove the direct installer command, or require explicit user confirmation with a pinned and verified source before installation.
  2. FIX-002
    Low
    Documentation examples use placeholder external domains and environment variables that trigger security scanners.
    Label examples as placeholders and separate executable setup steps from explanatory reference material.

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