messagebird
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage via npm to interface with the platform services. - [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI to perform operations such as logging in, connecting to services, and running automated actions. - [PROMPT_INJECTION]: The skill processes data from external communication channels (SMS, Voice, WhatsApp) which represents a surface for indirect instructions.
- Ingestion points: Content retrieved from MessageBird messages and conversation participants via
action runoutputs. - Boundary markers: None explicitly implemented in the skill instructions.
- Capability inventory: Subprocess execution via the
membraneCLI and the ability to create new actions dynamically on the Membrane platform. - Sanitization: Relies on the platform's internal handling of action parameters and outputs.
Audit Metadata