safegraph
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@membranehq/clipackage to interact with the platform. This is the official command-line interface provided by the vendor (membranedev) for managing integrations and authentication. - [COMMAND_EXECUTION]: The skill provides instructions for using the
membraneCLI to search for connectors, establish connections, and run actions. These are standard operations for the platform and do not involve unauthorized privilege escalation or dangerous command patterns. - [DATA_EXFILTRATION]: No evidence of unauthorized data transfer was found. The skill leverages Membrane's proxy system to securely interact with the SafeGraph API, ensuring that authentication headers and sensitive data are handled server-side rather than exposed in local scripts.
Audit Metadata