mx-toolbox
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clinpm package. This is a legitimate tool provided by the vendor (Membrane) for managing integrations. - [COMMAND_EXECUTION]: The skill uses the
membraneCLI tool to perform various operations, including connection management, action discovery, and executing API requests to Mx Toolbox. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes data from the Mx Toolbox API. Ingestion points: API responses retrieved via
membrane requestormembrane action run. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are mentioned in the skill. Capability inventory: The skill has the capability to execute actions and perform network requests via the CLI. Sanitization: No explicit validation or sanitization of external API data is described.
Audit Metadata