testing-mcp-tools-locally

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This document explicitly instructs placing a personal API token verbatim into curl/CLI headers and prints minted tokens (e.g., "Authorization: Bearer " and printing the minted token), which requires the agent to handle or emit secret values directly and therefore poses an exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The README instructs runtime calls to the MCP endpoint http://localhost:3001/mcp (used by the Inspector CLI for discovery/invocation), which returns tool definitions including an exec tool that can directly control agent tool invocations and thus agent instructions.