skills/szoloth/skills/mcporter/Gen Agent Trust Hub

mcporter

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the local environment using the mcporter CLI utility. It provides instructions to list tools, call specific functions, and generate standalone binaries using the --compile flag.
  • [PROMPT_INJECTION]: The skill acts as an interface for external MCP servers. This creates an indirect prompt injection surface where the agent processes data from external tool outputs.
  • Ingestion points: Data enters the context via mcporter list (tool schemas) and mcporter call (tool results).
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill can execute CLI commands via the mcporter binary.
  • Sanitization: There is no evidence of sanitization or validation of the data returned by external MCP servers before it is processed by the agent.
  • [DATA_EXPOSURE]: The skill is designed to read local configuration files, specifically ~/config/mcporter.json and existing configurations from Claude and Cursor, to discover and manage MCP server settings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 08:26 PM
Security Audit — agent-trust-hub — mcporter