skills/steipete/clawdis/mcporter/Gen Agent Trust Hub

mcporter

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the mcporter CLI which has the capability to execute local commands, specifically when using the --stdio flag to run MCP servers locally (e.g., mcporter call --stdio "bun run ./server.ts").
  • [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the mcporter package from the npm registry (Node.js).
  • [DATA_EXFILTRATION]: The skill documents the use of mcporter auth and mcporter config login to manage credentials and authentication tokens for external MCP servers. It also supports calling full URLs, which involves network operations.
  • [PROMPT_INJECTION]: As a tool designed to ingest data from external MCP servers via mcporter call, it possesses an indirect prompt injection surface.
  • Ingestion points: Tool outputs returned from HTTP or stdio MCP servers.
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: File system access (config management), network operations (HTTP servers, OAuth), and subprocess execution (stdio servers).
  • Sanitization: The skill instructions do not specify sanitization for the data retrieved from external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 02:55 AM