The Agent Skills Directory

[COMMAND_EXECUTION]: The skill guides the agent to use the mcporter CLI and includes examples of running arbitrary local scripts using the --stdio flag, such as bun run ./server.ts.
[EXTERNAL_DOWNLOADS]: The skill connects to and retrieves information from remote MCP servers via URLs (e.g., https://mcp.linear.app/mcp).
[DATA_EXFILTRATION]: The documentation recommends passing secrets like LINEAR_API_KEY via environment variables. While this is a standard practice, the mcporter call command transmits data to external MCP server endpoints.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing data from external MCP servers.
Ingestion points: Results and metadata from mcporter list and mcporter call (SKILL.md).
Boundary markers: None identified.
Capability inventory: Shell command execution and remote network requests.
Sanitization: No explicit sanitization of external server output is documented.

mcporter