mcporter
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the mcporter package via Node.js as part of its setup process. This is a standard installation for the tool provided by the vendor.
- [COMMAND_EXECUTION]: The documentation describes how to use the CLI to execute commands locally, including a mode to run servers via stdio (e.g., using bun run), which is an intended feature for developers testing local MCP servers.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Data entering the agent context via responses from remote or local MCP servers called through mcporter call (SKILL.md).
- Boundary markers: None specified in the documentation.
- Capability inventory: The skill provides broad capabilities to interact with external tools and APIs, including authentication support.
- Sanitization: No explicit sanitization or filtering of server output is described in the prompt instructions.
Audit Metadata