The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the mcporter CLI's --stdio flag to execute shell commands for starting local MCP servers.
[DATA_EXFILTRATION]: The tool can make network requests to remote MCP endpoints and manages sensitive authentication tokens through its configuration and authentication commands.
[EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the mcporter package from the Node.js package registry.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities due to its reliance on data from external MCP servers.
Ingestion points: Data retrieved from remote or local MCP servers via the mcporter call command.
Boundary markers: No explicit delimiters or instructions to disregard embedded commands are present in the skill content.
Capability inventory: The CLI tool can execute shell commands and perform network operations.
Sanitization: There is no evidence of sanitization or validation of the data received from external tools.

mcporter