cli-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install an external NPM package 'omniroute' globally (
npm install -g omniroute) or execute it vianpx. This package is not hosted by a recognized trusted organization or well-known service listed in the analysis configuration. - [COMMAND_EXECUTION]: The core functionality of the skill involves executing shell commands through the 'omniroute' utility to inspect MCP status, restart services, and perform tool calls.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external MCP tools using the
omniroute mcp callcommand. This data is passed into the agent context, creating a potential surface for indirect prompt injection if the tool output contains untrusted or malicious instructions. - Ingestion points: Output returned from
omniroute mcp call <tool>. - Boundary markers: No explicit delimiters or 'ignore' instructions are defined for the tool output.
- Capability inventory: The skill can execute commands, manage local services (restart), and perform network operations via tools.
- Sanitization: There are no documented sanitization or validation steps for the data received from tool calls.
Audit Metadata