kinde-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mentions the third-party tool mcp-remote (geelen/mcp-remote) which is featured in Kinde's official Claude Desktop documentation. The skill includes a specific security rule requiring users to use a pinned version and verify provenance before use.
  • [CREDENTIALS_UNSAFE]: The documentation correctly uses placeholders such as YOUR_API_KEY and YOUR_BUSINESS in all configuration examples. It explicitly warns against committing real bearer tokens and instructs users to store secrets outside of version control.
  • [COMMAND_EXECUTION]: The skill provides the official CLI command for adding an MCP server to Claude (claude mcp add). This is a standard administrative task for the tool's intended purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes OpenAPI specifications to generate tools (Category 8c). However, it implements strong boundary markers by requiring runtime tool discovery and referencing an authoritative operations matrix ([OPERATIONS.md]) to validate capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 09:07 PM
Security Audit — agent-trust-hub — kinde-mcp