mcporter
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local environment using the
mcporterCLI utility. It provides instructions to list tools, call specific functions, and generate standalone binaries using the--compileflag. - [PROMPT_INJECTION]: The skill acts as an interface for external MCP servers. This creates an indirect prompt injection surface where the agent processes data from external tool outputs.
- Ingestion points: Data enters the context via
mcporter list(tool schemas) andmcporter call(tool results). - Boundary markers: None specified in the instructions.
- Capability inventory: The skill can execute CLI commands via the
mcporterbinary. - Sanitization: There is no evidence of sanitization or validation of the data returned by external MCP servers before it is processed by the agent.
- [DATA_EXPOSURE]: The skill is designed to read local configuration files, specifically
~/config/mcporter.jsonand existing configurations from Claude and Cursor, to discover and manage MCP server settings.
Audit Metadata