mcporter

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the 'mcporter' Node.js package from the npm registry.
  • [COMMAND_EXECUTION]: The skill documentation demonstrates how to use the '--stdio' argument to execute local commands and scripts, such as running local servers with 'bun'.
  • [REMOTE_CODE_EXECUTION]: The CLI enables interaction with remote MCP servers via URLs, allowing the agent to fetch and process data or logic defined by third parties.
  • [DATA_EXFILTRATION]: The tool manages authentication tokens and server configurations through 'mcporter auth' and 'mcporter config' commands, which involve reading and writing potentially sensitive configuration files.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external MCP servers, creating an attack surface for indirect prompt injection.
  • Ingestion points: Tool outputs received from 'mcporter call' (SKILL.md).
  • Boundary markers: None identified; there are no instructions provided to the agent to treat external tool outputs as untrusted or to use specific delimiters.
  • Capability inventory: The skill can execute subprocesses via stdio, access arbitrary network URLs, and modify local configuration files.
  • Sanitization: None; responses from external MCP servers are processed and returned to the agent without explicit validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM