mcp-openapi-proxy

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install a binary directly from a GitHub repository using go install github.com/rendis/mcp-openapi-proxy/cmd/mcp-openapi-proxy@latest. This is a standard installation method for Go-based tools but involves fetching and executing external code.
  • [COMMAND_EXECUTION]: The skill provides instructions to execute various shell commands for installation (go install), initialization (swag init), conversion (swagger2openapi), and tool operation (mcp-openapi-proxy login/status/logout).
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of OpenAPI specifications provided via the MCP_SPEC variable, which can be a URL. This creates a surface for indirect prompt injection.
  • Ingestion points: OpenAPI 3.x specifications loaded from local paths or remote URLs defined in MCP_SPEC.
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided in the skill documentation.
  • Capability inventory: The skill allows the agent to make network requests (call_endpoint) and read specification files.
  • Sanitization: There is no mention of sanitization or schema validation performed on the ingested OpenAPI content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:51 PM