mastergo-magic-skill

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code or malicious instructions. It outlines a standard professional workflow for design automation using the MasterGo platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests design identifiers (fileId, layerId) and short links from users to process design data. While this represents a potential attack surface for indirect prompt injection from malicious design files, no specific exploitable patterns are present in the provided instructions.
  • Ingestion points: User-provided inputs including shortLink, fileId, and layerId as described in SKILL.md and examples.md.
  • Boundary markers: Not specified in the current workflow instructions.
  • Capability inventory: The skill uses the mcp__getD2c tool to generate and save frontend code and assets to the local filesystem.
  • Sanitization: No specific content sanitization or validation logic is defined in the instruction text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 07:27 AM
Security Audit — agent-trust-hub — mastergo-magic-skill