agent-native-framework

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx @agent-native/core for project scaffolding and adding visual planning capabilities. These packages are part of the vendor's own namespace (Aradotso) and are used for their intended purpose of application initialization.
  • [COMMAND_EXECUTION]: Standard development commands such as pnpm install, pnpm dev, and pnpm build are documented. These are restricted to the local development environment and are expected for the described workflow.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs users to manage sensitive credentials like DATABASE_URL and OPENAI_API_KEY using environment variables (.env files), which is a standard security best practice to avoid hardcoding secrets.
  • [SAFE]: Code snippets demonstrate communication with external services (e.g., search, email, and payment providers) using generic placeholders and fetch requests. These serve as architectural examples and do not involve unauthorized data transmission or exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 10:00 PM
Security Audit — agent-trust-hub — agent-native-framework