listenhub
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to automatically install the
@marswave/listenhub-clipackage from the NPM registry. This package is identified as a resource provided by the vendor (marswaveai). - [COMMAND_EXECUTION]: Execution of
listenhubCLI commands is required for checking authentication status and logging in. These are standard operations for tool integration, though the skill requests they be performed without manual user intervention. - [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted user input (messages) to determine which specialized skill to route to, creating a potential surface for prompt injection.
- Ingestion points: User intents are identified directly from the user's message in the 'How to Route' section.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are provided within the routing logic.
- Capability inventory: The skill environment includes the ability to install packages via
npm installand execute vendor shell commands. - Sanitization: The instructions do not specify any sanitization, validation, or filtering of the user input before intent classification.
Audit Metadata