Versioned security assessment

Report ID: SA-3F6E026A

7/21/2026, 2:53:20 AM

bnbchain-mcp security assessment v2

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: claude Latest published report
Skill name
bnbchain-mcp
Version
v1.0.0
Maintainer
internet-court
Source
github.com/internet-court/internet-court-skill/tree/main/vendored/bnb-chain/bnbchain-mcp
Coverage
5 Files scanned · 360 Lines analyzed
Policy version
skillstore-security-audit-policy-v1

Highest confirmed finding severity

High

3 confirmed security findings require attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

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

Static detections for private keys, shell execution, URLs, and address analysis are documentation-format false positives. The skill nevertheless enables high-impact blockchain writes and local file transfers, and it installs an unpinned npm package at runtime. Its explicit confirmation and key-handling guidance mitigate, but do not remove, these operational risks.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

Audit attestation

Attestation unavailable

No public attestation is available for this report.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

5 Files scanned · 360 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

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  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.

Not recorded by this audit

Env variables

May read values from the process environment.

Observed in 12 evidence locations

External commands

May invoke commands or programs outside the Skill.

Observed in 23 evidence locations

Risk findings

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

Confirmed security concerns (3)

RISK-001 High
SKILL.md:68SKILL.md:114-115references/greenfield-tools-reference.md:49
Financial and Irreversible Write Operations
The skill enables token transfers, token approvals, contract writes, and an irreversible Greenfield refund change. These actions can cause loss of funds or permanent account changes if the user confirms incorrect parameters.
The references expressly identify state-changing, irreversible operations, while the skill supplies confirmation guidance. The danger remains inherent to the supported operations.
RISK-002 Medium
SKILL.md:16SKILL.md:34
Unpinned Runtime Package Installation
The setup instructs clients to run the latest npm package at runtime. A later package release can change the code executed by the MCP server.
The documented command uses @latest and the configuration repeats it. This is direct evidence of an unpinned dependency execution path.
RISK-003 Medium
references/greenfield-tools-reference.md:29-30references/greenfield-tools-reference.md:34
Local File Transfer Through Greenfield Tools
Greenfield upload and download tools accept local file paths. Incorrect path selection can disclose local data to a bucket or overwrite a local destination.
The documentation explicitly supports absolute upload paths and download target paths. It does not show malicious intent, but the file-transfer capability has a clear data-handling impact.

Remediation

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

  1. FIX-001
    High
    Supported tools can transfer assets, approve spending, write contracts, and make irreversible Greenfield changes.
    Require explicit confirmation that repeats the network, recipient or contract, asset, amount, and irreversible effect before every write.
  2. FIX-002
    High
    Some reference entries accept private keys as tool parameters.
    Prefer a dedicated signing environment variable or wallet provider and reject private keys supplied through chat or tool arguments.
  3. FIX-003
    Medium
    The MCP server is installed from npm with the @latest tag.
    Pin a reviewed package version or integrity-controlled release, and document the update review process.
  4. FIX-004
    Medium
    Greenfield operations accept local upload and download paths.
    Require explicit confirmation of each source or destination path and limit access to user-approved workspace paths where possible.

Expert evidence

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

Artifact subject

Marketplace commit
3f6e026a3363e0954ede7bef0cfe88d4475de137
Content hash
4d609d55c1a1a02ebee2d2ec3718a10566078d81261dbf0e5e08f5c3896101fe
Tree hash
0f0ade1f32ef42375a594586680eb99bf384c00d4861e17bdbe4c90f488e5b13
Skill path
skills/internet-court/bnbchain-mcp
Audit payload hash
5d4c91e5a8030e94f11e38498f71978a

Analysis metadata

Audit model: claude

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 Source

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

Audit attestation: unavailable