Trust Engine/MCP Server

goldmembrane/cleaner-code

AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, and dependency attacks in AI-generated code. Static analysis + CodeBERT deep learning. Runs locally.

1 starsHTMLMITai-securitycode-analysiscodebertglassworm
REVIEWED79/100

Scanned 2026-07-07 · gemini v1

Dimension breakdown

Security

75/100

3 findings

Quality

75/100

10 findings

License

75/100

2 findings

Completeness

95/100

1 finding

Findings (16)

CRITICAL: 2HIGH: 1MEDIUM: 5LOW: 5INFO: 3
  • CRITICALqualityLack of Automated Tests
  • CRITICALlicenseCommercial-use restriction contradicts MIT license
  • HIGHqualityLicense Inconsistency
  • MEDIUMsecuritySSRF via Environment Variable Configuration
  • MEDIUMsecurityPotential Command Injection in AI Analyzer IPC

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Trust badge — flat styleTrust badge — for-the-badge style

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/goldmembrane/cleaner-code.svg)](https://archimedes.market/r/goldmembrane/cleaner-code)

HTML

<a href="https://archimedes.market/r/goldmembrane/cleaner-code"><img src="https://archimedes.market/api/badge/goldmembrane/cleaner-code.svg" alt="Archimedes Trust Verified"/></a>