Validate Databricks CLI token scopes against SDK configuration

NEXT_CHANGELOG.md

@@ -5,6 +5,7 @@
 ### New Features and Improvements
 
 ### Bug Fixes
+* Fixed Databricks CLI authentication to detect when the cached token's scopes don't match the SDK's configured scopes. Previously, a scope mismatch was silently ignored, causing requests to use wrong permissions. The SDK now raises an error with instructions to re-authenticate.
 
 ### Security Vulnerabilities
 

databricks-sdk-java/src/main/java/com/databricks/sdk/core/DatabricksCliCredentialsProvider.java

@@ -2,8 +2,13 @@
 
 import com.databricks.sdk.core.oauth.CachedTokenSource;
 import com.databricks.sdk.core.oauth.OAuthHeaderFactory;
+import com.databricks.sdk.core.oauth.Token;
+import com.databricks.sdk.core.oauth.TokenSource;
 import com.databricks.sdk.core.utils.OSUtils;
 import com.databricks.sdk.support.InternalApi;
+import com.fasterxml.jackson.core.JsonProcessingException;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import java.nio.charset.StandardCharsets;
 import java.util.*;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -15,6 +20,22 @@ public class DatabricksCliCredentialsProvider implements CredentialsProvider {
 
   public static final String DATABRICKS_CLI = "databricks-cli";
 
+  private static final ObjectMapper MAPPER = new ObjectMapper();
+
+  /** Thrown when the cached CLI token's scopes don't match the SDK's configured scopes. */
+  static class ScopeMismatchException extends DatabricksException {
+    ScopeMismatchException(String message) {
+      super(message);
+    }
+  }
+
+  /**
+   * offline_access controls whether the IdP issues a refresh token. It does not grant any API
+   * permissions, so its presence or absence should not cause a scope mismatch error.
+   */
+  private static final Set<String> SCOPES_IGNORED_FOR_COMPARISON =
+      Collections.singleton("offline_access");
+
   @Override
   public String authType() {
     return DATABRICKS_CLI;
@@ -92,13 +113,41 @@ public OAuthHeaderFactory configure(DatabricksConfig config) {
         return null;
       }
 
+      // Wrap the token source with scope validation so that every token — both the
+      // initial fetch and subsequent refreshes — is checked against the configured scopes.
+      TokenSource effectiveSource;
+      if (config.isScopesExplicitlySet()) {
+        List<String> scopes = config.getScopes();
+        effectiveSource =
+            new TokenSource() {
+              @Override
+              public Token getToken() {
+                Token t = tokenSource.getToken();
+                validateTokenScopes(t, scopes, host);
+                return t;
+              }
+            };
+      } else {
+        effectiveSource = tokenSource;
+      }
+
       CachedTokenSource cachedTokenSource =
-          new CachedTokenSource.Builder(tokenSource)
+          new CachedTokenSource.Builder(effectiveSource)
               .setAsyncDisabled(config.getDisableAsyncTokenRefresh())
               .build();
       cachedTokenSource.getToken(); // We need this for checking if databricks CLI is installed.
 
       return OAuthHeaderFactory.fromTokenSource(cachedTokenSource);
+    } catch (ScopeMismatchException e) {
+      // Scope validation failed. When the user explicitly selected databricks-cli auth,
+      // surface the mismatch immediately so they get an actionable error. When we're being
+      // tried as part of the default credential chain, step aside so other providers get
+      // a chance.
+      if (DATABRICKS_CLI.equals(config.getAuthType())) {
+        throw e;
+      }
+      LOG.warn("Databricks CLI token scope mismatch, skipping: {}", e.getMessage());
+      return null;
     } catch (DatabricksException e) {
       String stderr = e.getMessage();
       if (stderr.contains("not found")) {
@@ -112,4 +161,91 @@ public OAuthHeaderFactory configure(DatabricksConfig config) {
       throw e;
     }
   }
+
+  /**
+   * Validate that the token's scopes match the requested scopes from the config.
+   *
+   * <p>The {@code databricks auth token} command does not accept scopes yet. It returns whatever
+   * token was cached from the last {@code databricks auth login}. If a user configures specific
+   * scopes in the SDK config but their cached CLI token was issued with different scopes, requests
+   * will silently use the wrong scopes. This check surfaces that mismatch early with an actionable
+   * error telling the user how to re-authenticate with the correct scopes.
+   */
+  static void validateTokenScopes(Token token, List<String> requestedScopes, String host) {
+    Map<String, Object> claims = getJwtClaims(token.getAccessToken());
+    if (claims == null) {
+      LOG.debug("Could not decode token as JWT to validate scopes");
+      return;
+    }
+
+    Object tokenScopesRaw = claims.get("scope");
+    if (tokenScopesRaw == null) {
+      LOG.debug("Token does not contain 'scope' claim, skipping scope validation");
+      return;
+    }
+
+    Set<String> tokenScopes = parseScopeClaim(tokenScopesRaw);
+    if (tokenScopes == null) {
+      LOG.debug("Unexpected 'scope' claim type: {}", tokenScopesRaw.getClass());
+      return;
+    }
+
+    tokenScopes.removeAll(SCOPES_IGNORED_FOR_COMPARISON);
+    Set<String> requested = new HashSet<>(requestedScopes);
+    requested.removeAll(SCOPES_IGNORED_FOR_COMPARISON);
+
+    if (!tokenScopes.equals(requested)) {
+      List<String> sortedTokenScopes = new ArrayList<>(tokenScopes);
+      Collections.sort(sortedTokenScopes);
+      List<String> sortedRequested = new ArrayList<>(requested);
+      Collections.sort(sortedRequested);
+
+      throw new ScopeMismatchException(
+          String.format(
+              "Token issued by Databricks CLI has scopes %s which do not match "
+                  + "the configured scopes %s. Please re-authenticate "
+                  + "with the desired scopes by running `databricks auth login` with the --scopes flag."
+                  + "Scopes default to all-apis.",
+              sortedTokenScopes, sortedRequested));
+    }
+  }
+
+  /**
+   * Decode a JWT access token and return its payload claims. Returns null if the token is not a
+   * valid JWT.
+   */
+  private static Map<String, Object> getJwtClaims(String accessToken) {
+    String[] parts = accessToken.split("\\.");
+    if (parts.length != 3) {
+      LOG.debug("Tried to decode access token as JWT, but failed: {} components", parts.length);
+      return null;
+    }
+    try {
+      byte[] payloadBytes = Base64.getUrlDecoder().decode(parts[1]);
+      String payloadJson = new String(payloadBytes, StandardCharsets.UTF_8);
+      @SuppressWarnings("unchecked")
+      Map<String, Object> claims = MAPPER.readValue(payloadJson, Map.class);
+      return claims;
+    } catch (IllegalArgumentException | JsonProcessingException e) {
+      LOG.debug("Failed to decode JWT claims: {}", e.getMessage());
+      return null;
+    }
+  }
+
+  /**
+   * Parse the JWT "scope" claim, which can be either a space-delimited string or a JSON array.
+   * Returns null if the type is unexpected.
+   */
+  private static Set<String> parseScopeClaim(Object scopeClaim) {
+    if (scopeClaim instanceof String) {
+      return new HashSet<>(Arrays.asList(((String) scopeClaim).split("\\s+")));
+    } else if (scopeClaim instanceof List) {
+      Set<String> scopes = new HashSet<>();
+      for (Object s : (List<?>) scopeClaim) {
+        scopes.add(String.valueOf(s));
+      }
+      return scopes;
+    }
+    return null;
+  }
 }

databricks-sdk-java/src/main/java/com/databricks/sdk/core/DatabricksConfig.java

@@ -434,6 +434,15 @@ public DatabricksConfig setScopes(List<String> scopes) {
     return this;
   }
 
+  /**
+   * Returns true if scopes were explicitly configured (either directly in code or loaded from a
+   * config file). When scopes are not set, getScopes() defaults to ["all-apis"], which would cause
+   * false-positive mismatches during scope validation.
+   */
+  boolean isScopesExplicitlySet() {
+    return scopes != null && !scopes.isEmpty();
+  }
+
   public String getProfile() {
     return profile;
   }

databricks-sdk-java/src/test/java/com/databricks/sdk/core/DatabricksCliCredentialsProviderTest.java

@@ -139,4 +139,13 @@ void testBuildHostArgs_UnifiedHostFalse_WithAccountHost() {
             CLI_PATH, "auth", "token", "--host", ACCOUNT_HOST, "--account-id", ACCOUNT_ID),
         cmd);
   }
+
+  @Test
+  void testScopesExplicitlySetFlag() {
+    DatabricksConfig config = new DatabricksConfig();
+    assertFalse(config.isScopesExplicitlySet());
+
+    config.setScopes(Arrays.asList("sql", "clusters"));
+    assertTrue(config.isScopesExplicitlySet());
+  }
 }

databricks-sdk-java/src/test/java/com/databricks/sdk/core/DatabricksCliScopeValidationTest.java

@@ -0,0 +1,132 @@
+package com.databricks.sdk.core;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+import com.databricks.sdk.core.oauth.Token;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import java.nio.charset.StandardCharsets;
+import java.time.Instant;
+import java.util.*;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.MethodSource;
+
+class DatabricksCliScopeValidationTest {
+
+  private static final String HOST = "https://my-workspace.cloud.databricks.com";
+  private static final ObjectMapper MAPPER = new ObjectMapper();
+
+  /** Builds a fake JWT (header.payload.signature) with the given claims. */
+  private static String makeJwt(Map<String, Object> claims) {
+    try {
+      String header =
+          Base64.getUrlEncoder()
+              .withoutPadding()
+              .encodeToString("{\"alg\":\"none\"}".getBytes(StandardCharsets.UTF_8));
+      String payload =
+          Base64.getUrlEncoder().withoutPadding().encodeToString(MAPPER.writeValueAsBytes(claims));
+      return header + "." + payload + ".sig";
+    } catch (Exception e) {
+      throw new RuntimeException(e);
+    }
+  }
+
+  private static Token makeToken(Map<String, Object> claims) {
+    return new Token(makeJwt(claims), "Bearer", Instant.now().plusSeconds(3600));
+  }
+
+  static List<Arguments> scopeValidationCases() {
+    return Arrays.asList(
+        // Exact match (offline_access filtered out).
+        Arguments.of(
+            Collections.singletonMap("scope", "sql offline_access"),
+            Collections.singletonList("sql"),
+            false,
+            "match"),
+        // Mismatch throws.
+        Arguments.of(
+            Collections.singletonMap("scope", "all-apis offline_access"),
+            Collections.singletonList("sql"),
+            true,
+            "mismatch"),
+        // offline_access on token only — still equivalent.
+        Arguments.of(
+            Collections.singletonMap("scope", "all-apis offline_access"),
+            Collections.singletonList("all-apis"),
+            false,
+            "offline_access_on_token_only"),
+        // offline_access in config only — still equivalent.
+        Arguments.of(
+            Collections.singletonMap("scope", "all-apis"),
+            Arrays.asList("all-apis", "offline_access"),
+            false,
+            "offline_access_in_config_only"),
+        // Scope claim as list instead of string.
+        Arguments.of(
+            new HashMap<String, Object>() {
+              {
+                put("scope", Arrays.asList("sql", "offline_access"));
+              }
+            },
+            Collections.singletonList("sql"),
+            false,
+            "scope_as_list"));
+  }
+
+  @ParameterizedTest(name = "{3}")
+  @MethodSource("scopeValidationCases")
+  void testScopeValidation(
+      Map<String, Object> tokenClaims,
+      List<String> configuredScopes,
+      boolean expectError,
+      String testName) {
+    Token token = makeToken(tokenClaims);
+
+    if (expectError) {
+      assertThrows(
+          DatabricksCliCredentialsProvider.ScopeMismatchException.class,
+          () ->
+              DatabricksCliCredentialsProvider.validateTokenScopes(token, configuredScopes, HOST));
+    } else {
+      assertDoesNotThrow(
+          () ->
+              DatabricksCliCredentialsProvider.validateTokenScopes(token, configuredScopes, HOST));
+    }
+  }
+
+  @Test
+  void testNoScopeClaimSkipsValidation() {
+    Token token = makeToken(Collections.singletonMap("sub", "user@example.com"));
+    assertDoesNotThrow(
+        () ->
+            DatabricksCliCredentialsProvider.validateTokenScopes(
+                token, Collections.singletonList("sql"), HOST));
+  }
+
+  @Test
+  void testNonJwtTokenSkipsValidation() {
+    Token token = new Token("opaque-token-string", "Bearer", Instant.now().plusSeconds(3600));
+    assertDoesNotThrow(
+        () ->
+            DatabricksCliCredentialsProvider.validateTokenScopes(
+                token, Collections.singletonList("sql"), HOST));
+  }
+
+  @Test
+  void testErrorMessageContainsReauthCommand() {
+    Token token = makeToken(Collections.singletonMap("scope", "all-apis"));
+    DatabricksCliCredentialsProvider.ScopeMismatchException e =
+        assertThrows(
+            DatabricksCliCredentialsProvider.ScopeMismatchException.class,
+            () ->
+                DatabricksCliCredentialsProvider.validateTokenScopes(
+                    token, Arrays.asList("sql", "offline_access"), HOST));
+    assertTrue(
+        e.getMessage().contains("databricks auth login"),
+        "Expected re-auth command in error message, got: " + e.getMessage());
+    assertTrue(
+        e.getMessage().contains("do not match the configured scopes"),
+        "Expected scope mismatch details in error message, got: " + e.getMessage());
+  }
+}