skills/craftos-dev/craftbot/mcporter/Gen Agent Trust Hub

mcporter

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill setup involves installing the mcporter package from the public Node.js registry.
  • [COMMAND_EXECUTION]: The mcporter CLI is capable of executing shell commands to start local MCP servers via the --stdio interface.
  • [DATA_EXFILTRATION]: The skill can perform network requests to arbitrary URLs and manage authentication tokens for MCP tool interaction.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection from untrusted MCP servers.
  • Ingestion points: Responses from tools called via the mcporter CLI (SKILL.md).
  • Boundary markers: No delimiters or safety instructions are defined to separate tool output from instructions.
  • Capability inventory: Shell command execution through stdio and network requests through HTTP tool calls (SKILL.md).
  • Sanitization: No sanitization or validation of tool outputs is present in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:35 PM
Security Audit — agent-trust-hub — mcporter