system-design-skills

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements an architecture-as-code workflow using the legitimate LikeC4 toolset (github.com/likec4/likec4). All CLI commands and execution patterns are documented and restricted to architecture validation, site building, and diagram export.
  • [SAFE]: Data ingestion is limited to eliciting system design details from the user to generate markdown and DSL files. No evidence of malicious prompt injection or unauthorized data access was found.
  • [SAFE]: External dependencies and remote code execution patterns are standard for the tech stack (e.g., using npx or bunx to run the likec4 CLI) and do not involve suspicious third-party domains or unverified scripts.
  • [SAFE]: The mention of environment variables like LEANIX_API_TOKEN is correctly scoped as documentation for intended integration with external architecture inventory services.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 10:59 AM
Security Audit — agent-trust-hub — system-design-skills