draw-json-architecture

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates its workflow by executing local Node.js scripts provided within the skill's package, such as validate.mjs, audit-claims.mjs, and builder.mjs. It also utilizes execSync to run standard git commands (e.g., git remote get-url, git rev-parse) to derive repository metadata and default branch names for generating source code links.
  • [SAFE]: All identified behaviors, including repository research, local file modification, and script execution, are directly related to the skill's primary purpose of generating architecture documentation. No network exfiltration, hardcoded credentials, or malicious obfuscation patterns were detected. The generated HTML viewer is self-contained and operates entirely on the local machine.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 03:07 AM
Security Audit — agent-trust-hub — draw-json-architecture