switchboard
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from the npm registry to interact with the Membrane platform.- [COMMAND_EXECUTION]: It uses themembranecommand-line interface to perform authentication (membrane login), connection management (membrane connect), and action execution (membrane action run).- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from the Switchboard API which is then processed by the agent. - Ingestion points: Data returned from
membrane action runandmembrane requestcommands. - Boundary markers: None specified in the instructions to distinguish between data and instructions.
- Capability inventory: Ability to execute API actions and send arbitrary HTTP requests via the CLI.
- Sanitization: No data validation or escaping mechanisms are described.
Audit Metadata