mcporter

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'mcporter' package from the public Node package registry (NPM) as a core dependency for its operations.
  • [COMMAND_EXECUTION]: The skill instructions demonstrate the use of the '--stdio' flag (e.g., 'mcporter call --stdio "bun run ./server.ts"'), which allows for the execution of arbitrary shell commands to interface with local MCP servers.
  • [DYNAMIC_EXECUTION]: The 'generate-cli' and 'emit-ts' commands facilitate the generation of code and CLI tools based on external definitions, which may lead to the execution of generated scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external MCP servers, creating a vulnerability surface where malicious tool outputs could influence the agent.
  • Ingestion points: Outputs from 'mcporter call' commands fetching data from remote or local MCP servers (SKILL.md).
  • Boundary markers: None; instructions do not provide delimiters or instructions to ignore embedded commands in tool results.
  • Capability inventory: The skill has access to network requests, local command execution via stdio, and configuration file modification.
  • Sanitization: There is no evidence of sanitization or validation of the data returned by the MCP servers before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:32 PM
Security Audit — agent-trust-hub — mcporter