skills/elizaos/eliza/mcporter/Gen Agent Trust Hub

mcporter

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The mcporter CLI supports executing local commands through stdio, which is used to interface with local MCP servers as demonstrated by patterns like mcporter call --stdio "bun run ./server.ts".
  • [EXTERNAL_DOWNLOADS]: The skill initiates the installation of the mcporter package from the Node.js package registry and facilitates communication with remote MCP servers via HTTP URLs.
  • [DATA_EXFILTRATION]: The skill manages authentication tokens and facilitates remote tool calls to external MCP servers, which is part of its core functionality for server-to-server interaction.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates an ingestion point for external data from MCP server responses.
  • Ingestion points: Data returned from tools called via mcporter call (SKILL.md).
  • Boundary markers: Not explicitly defined in the CLI documentation for data returned from external tools.
  • Capability inventory: Subprocess execution via stdio calls, network operations for remote server access, and local file access for configuration management (SKILL.md).
  • Sanitization: No specific sanitization logic for third-party server output is documented within the CLI's instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 07:23 AM