DEV Community

Ken Fukuyama
Ken Fukuyama

Posted on • Edited on • Originally published at blog.kenev.net

Digging into API Authorization with OPA

#opa #openpolicyagent #authorization #abac

I've recently been getting my hands on with Open Policy Agent to find a way to gain a fine-grained permission control feature for my custom API service.

In this post I'm assuming you have at least heard what Open Policy Agent is. If you haven't, I definitely recommend watching the following presentations from Torin Sandal.

Intro: Open Policy Agent

OPA is extremely powerful and flexible. You should take a look at some of the tutorials in the official docs starting from the, well, "Get Started".

One tutorial I found very interesting is the HTTP API Authorization. I think many people have experienced API Authorization and have struggled all the if statements to allow or deny a user doing something. With OPA, you can delegate the decision outside of your code.

"Delegate the decision outside?", at first, this was hard for me to imagine so I've decided to migrate an API from a non-OPA version to an OPA version.

TL;DR

You can look at the full code in the repository.

GitHub logo kenfdev / opa-api-auth-go

A sample API using OPA as the Policy Decision Point.

OPA API Authorization

A sample to show the difference between using OPA as the Policy Decision Point.

How to

The master branch does not include OPA as the Policy Decision Point. OPA is added in the add-opa branch.

You can compare the difference in this PR

If you want to spin up the OPA version, do the following steps:

git checkout add-opa

docker-compose up
Enter fullscreen mode Exit fullscreen mode

Requesting the API

The API is available in the GET /finance/salary/:username endpoint. You can GET to this endpoint but a JWT is needed to properly make a request.

You can easily create an JWT at jwt.io. This application assumes that the algorithm is HS256 and the secret is simply secret. Also, the payload should look something like this:

{
  "sub": "1234567890"
  "iat": 1516239022,
  "user": "bob",
  "subordinates": ["alice"],
  "hr"
…
Enter fullscreen mode Exit fullscreen mode
View on GitHub
  • You can run the OPA authorized API from this branch of the repository
  • The diff of non-OPA version and OPA version can be found here

The API

The API we are going to use is based on the tutorial in the OPA official docs. The tutorial uses python but I've decided to build it with Go and with labstack's echo framework.

Here is the overview of the application (including the policies).

  • Members are as follows:
    • Alice
    • Bob
    • Charlie
    • Betty
    • David
  • Bob is Alice's manager and Betty is Charlie's manager. David belongs to the HR department.
  • Users can view their own salary
  • Managers can view their subordinates' salary
  • HRs can view everybody's salary

Here is an overview diagram.

Let's get started with the non-OPA version.

The Policy Decision without OPA

I've created a Policy Enforcement middleware to enforce the policy on every request made to the API endpoint. In the middleware, I'm simply asking a PolicyGateway to check if the requester is allowed to call the API. The code below shows the overview.(GitHub)

...
logrus.Info("Enforcing policy with middleware")

allow := gateway.Ask(c)

if allow {
    logrus.Info("Action is allowed, continuing process")
    return next(c)
} else {
    logrus.Info("Action was not allowed, cancelling process")
    return c.String(http.StatusForbidden, "Action not allowed")
}
...
Enter fullscreen mode Exit fullscreen mode

The interface for PolicyGateway is just 1 method Ask which returns a bool meaning Allow or Deny.

type PolicyGateway interface {
    Ask(echo.Context) bool
}
Enter fullscreen mode Exit fullscreen mode

I've called the implementation for the gateway the PolicyLocalGateway and basically the following code is what it does.(GitHub.

func (gw *PolicyLocalGateway) checkGETSalary(c echo.Context, claims *entity.TokenClaims) bool {
    userID := c.Param("id")

    if yes := gw.checkIfOwner(userID, claims); yes {
        logrus.Info("Allowing because requester is the owner")
        return true
    }

    if yes := gw.checkIfSubordinate(userID, claims); yes {
        logrus.Info("Allowing because target is a subordinate of requester")
        return true
    }

    if yes := gw.checkIfHR(claims); yes {
        logrus.Info("Allowing because requester is a member of HR")
        return true
    }

    logrus.Info("Denying request")
    return false
}
Enter fullscreen mode Exit fullscreen mode

You can see lots of if statements and can assume this will easily increase the amount of code in the long run. Also, it is a little hard to understand what is going on with all these if statements and indentation (well... that might be my fault, but you get the point).

Let's check some HTTP requests to see what happens.

First, let's start with Alice. Since Alice is a normal staff, she can only view her own salary.

$ curl -H "Authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwiaWF0IjoxNTE2MjM5MDIyLCJ1c2VyIjoiYWxpY2UiLCJzdWJvcmRpbmF0ZXMiOltdLCJociI6ZmFsc2V9.WTR-Or-vS1yFBFHk7UyqZxsNhtTNSWeazJ57SJ7V4qY" \
  http://localhost:1323/finance/salary/alice

100
Enter fullscreen mode Exit fullscreen mode

You can see that the value 100 came back with no errors. Let's see if Alice can view Bob's salary.

$ curl -H "Authorization: Bearer <Alice's JWT>" \
  http://localhost:1323/finance/salary/bob

Action not allowed
Enter fullscreen mode Exit fullscreen mode

It is now forbidden because Alice is a normal staff and cannot view other employee's salary. The logs show the request has been denied as well.

app_1  | msg="Enforcing policy with middleware"
app_1  | msg="Checking GET salary policies" claims="&{alice [] false { 0  1516239022  0 1234567890}}" userID=bob
app_1  | msg="Denying request"
app_1  | msg="Action was not allowed, cancelling process"
Enter fullscreen mode Exit fullscreen mode

On the other hand, let's see if Bob can view Alice's salary.

Bob's JWT payload looks like the following:

{
  "sub": "1234567890",
  "iat": 1516239022,
  "user": "bob",
  "subordinates": ["alice"],
  "hr": false
}
Enter fullscreen mode Exit fullscreen mode

He has alice as his subordinate which means he is Alice's manager.

$ curl -H "Authorization: Bearer <Bob's JWT>" \
  http://localhost:1323/finance/salary/alice

100
Enter fullscreen mode Exit fullscreen mode

You can confirm that Bob is allowed to view Alice's salary. This is checked in the logic gw.checkIfSubordinate in the code above. Now how about Bob viewing David's salary?

$ curl -H "Authorization: Bearer <Bob's JWT>" \
  http://localhost:1323/finance/salary/david

Action not allowed
Enter fullscreen mode Exit fullscreen mode

Of course, Bob is not allowed to view David's salary because he has no permission to do so.

Now, let's see what David as a member of HR can do?

David's JWT payload is as follows.

{
  "sub": "1234567890",
  "iat": 1516239022,
  "user": "david",
  "subordinates": [],
  "hr": true
}
Enter fullscreen mode Exit fullscreen mode

Since he is a member of HR, he has hr: true in his JWT payload.

$ curl -H "Authorization: Bearer <David's JWT>" \
  http://localhost:1323/finance/salary/bob

200
Enter fullscreen mode Exit fullscreen mode

Success! And he can also see Betty, Alice, Charlie's salary as well. This is because he passes the check gw.checkIfHR in the code above.

This should have been pretty straight forward. Now, let's see what happens when OPA comes into the game.

The Policy Decision with OPA

Adding OPA is pretty simple. The implementation of the PolicyGateway will change. I've called it the PolicyOpaGateway and this time, I didn't implement anything related to policy rules (none of those if statements anymore) because I wanted to delegate them to OPA.

The main changes are:

  • I wrote policies in Rego to *.rego files
  • I added the OPA server next to the main app
  • I have implemented the PolicyGateway to make an external HTTP request to the OPA server with enough payloads in order for OPA to make decisions

Writing the policy in Rego

The policy written in Rego is as below.

package httpapi.authz

# io.jwt.decode_verify
# https://www.openpolicyagent.org/docs/latest/language-reference/#tokens
token = t {
  [valid, _, payload] = io.jwt.decode_verify(input.token, { "secret": "secret" })
  t := {
    "valid": valid,
    "payload": payload
  }
}

default allow = false

# Allow users to get their own salaries.
allow {
  token.valid

  some username
  input.method == "GET"
  input.path = ["finance", "salary", username]
  token.payload.user == username
}

# Allow managers to get their subordinate's salaries.
allow {
  token.valid

  some username
  input.method == "GET"
  input.path = ["finance", "salary", username]
  token.payload.subordinates[_] == username
}

# Allow HR members to get anyone's salary.
allow {
  token.valid

  input.method == "GET"
  input.path = ["finance", "salary", _]
  token.payload.hr == true
}
Enter fullscreen mode Exit fullscreen mode

It is nearly identical with the tutorial version. A slight difference is that it is verifying the JWT token with io.jwt.decode_verify using the key secret.

Side Note: The Rego Playground

One awesome feature I want to point out about OPA is the Rego Playground.

You can write policies and quickly evaluate them on the browser! In addition, you can share the policy via a link for others to look at (e.g. they can debug your policies). Here's the link for the policy above. The Input is set to Alice's JWT and the path to her own salary.

https://play.openpolicyagent.org/p/ww8qdEHdn0

You can check the OUTPUT to see that the result is allowed.

Adding the OPA server

After creating a policy with Rego, I've set the OPA service next to the main app by adding the following lines in the docker-compose.yml.

  pdp:
    image: openpolicyagent/opa:0.12.0
    ports:
      - 8181:8181
    volumes:
      - ./opa:/etc/opt/opa
    command: ["run", "--server", "/etc/opt/opa/authz.rego"]
Enter fullscreen mode Exit fullscreen mode

FYI, PDP stands for Policy Decision Point. I just wanted to give it a generic name.

Requesting OPA for decisions

Now that OPA is ready, I have implemented the PolicyGateway so it makes an external HTTP request to OPA server for decisions.

Preparing the input

OPA needs enough information in order to make decisions. For this simple app, I needed to tell OPA:

  • Who the requester is - including attributes (JWT token)
  • What endpoint was requested (request path and HTTP method)

And the code looks like this. I have used echo's JWT middleware to easily extract the JWT data.

...
token := c.Get("token").(*jwt.Token)
// After splitting, the first element isn't necessary
// "/finance/salary/alice" -> ["", "finance", "salary", "alice"]
paths := strings.Split(c.Request().RequestURI, "/")[1:]
method := c.Request().Method

// create input to send to OPA
input := &opaInput{
    Token:  token.Raw,
    Path:   paths,
    Method: method,
}
// don't forget to wrap it with `input`
opaRequest := &opaRequest{
    Input: input,
}
...
Enter fullscreen mode Exit fullscreen mode

A slight gotcha is that the HTTP request payload needs to be wrapped with an input key as shown in the code above. Of course, this is mentioned in the docs.

HTTP Request

I have injected OPA's endpoint to the PolicyGateway through an environment variable (here and here). Therefore, it is accessible by calling gw.endpoint. So the request will be like the following code.(GitHub)

type opaResponse struct {
    Result bool `json:"result"`
}

...

// request OPA
resp, err := http.Post(gw.endpoint, "application/json", bytes.NewBuffer(requestBody))
...
body, err := ioutil.ReadAll(resp.Body)
...
var opaResponse opaResponse
err = json.Unmarshal(body, &opaResponse)
Enter fullscreen mode Exit fullscreen mode

It's simply asking OPA and returning the result back to the caller. Now that the code is prepared, let's give it a shot again!

# David (a member of HR) viewing Betty's salary
$ curl -H "Authorization: Bearer <David's JWT>" http://localhost:1323/finance/salary/betty

200
Enter fullscreen mode Exit fullscreen mode

Looks good. Let's look at the logs.

app_1  | msg="Enforcing policy with middleware"
app_1  | msg="Requesting PDP for decision" method=GET path="[finance salary betty]" token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwiaWF0IjoxNTE2MjM5MDIyLCJ1c2VyIjoiZGF2aWQiLCJzdWJvcmRpbmF0ZXMiOltdLCJociI6dHJ1ZX0.TBXtM_p-VIlgx9NSLn4An6hELr2UB3CrqHUJmofQorM
pdp_1  | l":"info","msg":"Sent response.","req_id":2,"req_method":"POST","req_path":"/v1/data/httpapi/authz/allow","resp_bytes":15,"resp_duration":4.1901,"resp_status":200,"time":"2019-06-30T14:29:52Z"}
app_1  | msg=Decision result=true
app_1  | msg="Action is allowed, continuing process"
app_1  | msg="Processing salary request" id=betty
app_1  | msg="Fetched salary" id=betty salary=200
Enter fullscreen mode Exit fullscreen mode

The app is requesting OPA and receiving true as the result. You can see the same result in the following playground.

https://play.openpolicyagent.org/p/w0kohf47we

Let's also see if Alice's request to Bob (to her manager) will fail.

$ curl -H "Authorization: Bearer <Alice's JWT>" \
  http://localhost:1323/finance/salary/bob

Action not allowed
Enter fullscreen mode Exit fullscreen mode

Awesome! And the logs?

app_1  | msg="Enforcing policy with middleware"
app_1  | msg="Requesting PDP for decision" method=GET path="[finance salary bob]" token=<Alice's JWT>
pdp_1  | l":"info","msg":"Received request.","req_id":1,"req_method":"POST","req_path":"/v1/data/httpapi/authz/allow","time":"2019-06-30T21:29:59Z"}
app_1  | msg=Decision result=false
app_1  | msg="Action was not allowed, cancelling process"
Enter fullscreen mode Exit fullscreen mode

Everything is working as expected! (Here's the playground)

We have successfully replaced the local policy engine to OPA. You can see how the separation of concerns are met by delegating the policy decisions to OPA.

You can view the full changes to the code in my PR here.

Wrap up

This was a very simple example to show how you can leverage the power of OPA with an HTTP API server.

Some Pros and Cons I can think of from this simple example is:

Pros
Separation of concerns. In my main app, I can concentrate on the business logic I need to implement. I don't have to write all those if statements and change my code each time a policy changes. If I change my code, that means I have to deploy it again. As for OPA, you can dynamically change your policies on the run. No redeploying is necessary when you change policies.

In addition, I was not able to mention it in this post, but Rego can be tested with Rego, too. You should have a look at "How Do I Test Policies?".

Some additional Pros I've heard in the slack channel are as follows:

  • Security/Compliance can audit policy separate from auditing the code.
  • Consistent logging of decisions; helpful for SIEM integration (Decision Logs)
  • Consistent policy language (Rego) across different microservices; helps people trying to understand what is actually authorized across a chain of services
  • When building a UI, it also needs to implement the same policies; easier if decoupled and consistent across services (e.g. take a look at Chef Automate's Introspection)
  • Start with a solution purpose-built where you can start simple but that grows with you as your authz needs evolve.
  • Avoid a series of one-off extensions to an authz system that in the end looks like a frankenstein. You can see how the monolith app I built above will become like in the long run.

Cons
I don't see a major downside in using OPA, but as this post has shown, a standard monolithic service turned into a microservice approach. Which means it will add complexity than not using OPA. But this is more about microservices than OPA itself. Also, Rego is an additional learning curve for newbies. I'd say it's worth the effort and I'm assuming Rego is going to become more and more popular as OPA grows.

Finally, some questions that may arise are:

Do I have to pass all information to OPA for decisions?
AFAIK, the simplest approach is to pass everything, but that may not be easy or performant in many situations. One way is to use the http.send built-in function to make external request from within OPA. You can also use Bundles for OPA to fetch data periodically from external services. Further information can be found in the official docs "Guides: Identity and User Attributes". It has really good detail in it.

Can I use OPA as a library?
Maybe you don't want an extra container for various reasons. Yes, OPA can be used as a Go library and you can look at some awesome OSS projects that use OPA as a library. Some that I know are:

Can I create something like an AWS IAM with OPA?
I have heard this question several times (including myself) in the OPA slack and if you have the same question, you should definitely look at the Chef Automate authorization service documentation. This document is amazing. I really mean it. There are definitely many ways to implement something like an AWS IAM with OPA but this one is surely a great live example.

I'm assuming there are many more questions, but the best way to get support is to join the OPA slack channel. The people there are super supportive and I've gained a lot of knowledge there.

Thank you for reading this long post!!! I'd like to greatly appreciate Ash(@ashtalk) and Tim(@tlhinrichs) for reviewing this post upfront! I'm hoping I can contribute and give back with what I have to the OPA community!

Reference

  • Deep Dive: Open Policy Agent

Top comments (0)

Read next

edgarcajusol profile image

¿Fraude? Que no nos engañe! Ramdom Forest Classifier

Edgar Cajusol -

swati_gupta_c3c15df8b06de profile image

Revolutionizing Compensation Management with SAP Enterprise Compensation Management

Swati Gupta -

mpalhutchinson profile image

Week 12: Release 0.3 pull request 2

mpa-LHutchinson -

swati_gupta_c3c15df8b06de profile image

Revolutionizing Customer Engagement: The Power of CPG Chat https://www.cloudastra.co/blogs/revolutionizing-customer-engagement-the-power-of-cpg-chat

Swati Gupta -