mcp-csharp-publish

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes command examples that embed secrets verbatim (e.g., --api-key YOUR_NUGET_API_KEY, --secrets api-key=my-actual-api-key, docker -e API_KEY=test-key), which would encourage an agent to output actual secret values in commands or configs.

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

• Potentially malicious external URL detected (high risk: 0.90). The CI example explicitly curls and writes the mcp-publisher binary from https://github.com/modelcontextprotocol/registry/releases/latest/download/mcp-publisher-linux-amd64 and then executes it (./mcp-publisher publish), so the skill fetches remote executable at runtime that is required for publishing and directly runs remote code.