base44-platform-connectors
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as legitimate documentation for platform-specific OAuth integrations. The instructions and code examples adhere to secure development practices, such as proper authentication checking and protecting sensitive tokens from being exposed to the frontend.
- [EXTERNAL_DOWNLOADS]: The documentation provides code examples that depend on the official vendor SDK, specifically the '@base44/sdk' package. These are recognized as legitimate vendor resources.
- [INDIRECT_PROMPT_INJECTION]: The skill enables applications to ingest data from third-party services (e.g., Google Calendar, Snowflake). While this creates an ingestion point for external data, the skill focuses on the connection infrastructure and includes best-practice advice on token handling.
- Ingestion points: Data is fetched from external APIs using OAuth tokens in backend and server functions.
- Boundary markers: No specific boundary markers are defined in the generic code templates.
- Capability inventory: The skill utilizes network operations (fetch) and platform-specific SDK methods for interacting with external services.
- Sanitization: The skill explicitly instructs developers to return only necessary data and never the access tokens themselves to the client-side code.
Audit Metadata