Versioned security assessment

Report ID: SA-1FBB7BBA

6/30/2026, 5:00:55 PM

mcp-builder-ms security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
mcp-builder-ms
Version
v2
Maintainer
sickn33
Source
github.com/sickn33/antigravity-awesome-skills/tree/main/skills/mcp-builder-ms
Coverage
1 Files scanned · 310 Lines analyzed
Policy version
Unavailable

Confirmed finding summary

No confirmed security findings

The completed audit recorded no confirmed security findings. This is not proof that the Skill has no side effects.

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 analysis reported many high-risk patterns, but review found this is a Markdown guide rather than executable code. The weak-cryptography and hidden-file findings are false positives; the meaningful risks are documented network fetches and example commands that users may run during MCP development.

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 · 310 Lines analyzed

2 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 10 evidence locations

Filesystem access

May read or write local files.

Not recorded by this audit

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 3 evidence locations

Capability review items (2)
Medium
SKILL.md:197SKILL.md:198SKILL.md:201
External Command Guidance Requires Review
The guide tells users to run npm, npx, and Python compile commands while testing MCP servers. This is legitimate development guidance, but npm scripts and local project files can execute arbitrary code if the target project is untrusted.
The commands are explicitly shown in the Markdown guide and are relevant to MCP testing. Risk depends on the surrounding project, so this is a real but contextual concern rather than confirmed malicious behavior.
Medium
SKILL.md:83SKILL.md:85SKILL.md:114SKILL.md:118SKILL.md:260SKILL.md:277SKILL.md:278
Network Fetch Guidance Is Expected But Material
The guide instructs users to fetch public MCP and SDK documentation from modelcontextprotocol.io and raw.githubusercontent.com. These are expected references for this skill, but the skill should be used with awareness that it directs network access.
The referenced URLs are visible in the guide and align with the stated MCP development purpose. I did not find evidence that sensitive data is sent to those URLs.

Risk findings

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

No confirmed security findings were recorded for this completed audit.

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 (2)
Low
SKILL.md:3SKILL.md:16SKILL.md:22SKILL.md:28SKILL.md:33SKILL.md:35SKILL.md:65SKILL.md:71SKILL.md:74SKILL.md:107SKILL.md:138SKILL.md:157SKILL.md:158SKILL.md:165SKILL.md:167SKILL.md:178SKILL.md:192SKILL.md:204SKILL.md:231SKILL.md:244SKILL.md:281
Weak Cryptography Static Findings Are False Positives
The static analyzer flagged weak cryptographic algorithm indicators across prose, headings, and Markdown examples. I did not find evidence of cryptographic code, hash functions, encryption APIs, or instructions to use weak algorithms.
The reviewed file is a documentation guide and the flagged lines do not implement cryptography. The repeated hits appear to come from token matches in prose and Markdown formatting.
Low
SKILL.md:100SKILL.md:121SKILL.md:271SKILL.md:279SKILL.md:296
Hidden File Access Static Findings Are False Positives
The hidden-file findings point to C#/.NET and Microsoft MCP references, not reads or writes to dotfiles. I did not find instructions to access hidden files or hidden directories.
Each flagged location is documentation text about .NET or Microsoft MCP resources. There is no file access operation at those lines.

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