branch
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the installation of the official Membrane CLI tool (@membranehq/cli) from the npm registry to enable interaction with the platform functionality. This is a standard vendor-provided resource.\n- [COMMAND_EXECUTION]: Instructions include using the
membraneCLI for authenticating with the service, managing connections, and executing actions within the Branch integration. All commands relate directly to the skill's stated purpose.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes data from the external Branch API. This is an inherent property of integration tools.\n - Ingestion points: Content retrieved through
membrane action runand action search results.\n - Boundary markers: No specific delimiters or instructions to disregard embedded commands are defined for the processed data.\n
- Capability inventory: Includes shell command execution via the CLI and action triggers on the Membrane platform.\n
- Sanitization: No specific validation or filtering logic for external data is described in the provided skill instructions.
Audit Metadata