This is an automated email from the ASF dual-hosted git repository.
dongjoon-hyun pushed a commit to branch branch-4.x
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.x by this push:
new 217f61536a88 [SPARK-58153][CORE][R] Reject JAR entries escaping the
extraction directory in `RPackageUtils`
217f61536a88 is described below
commit 217f61536a88aef671d1184622b12441b514851e
Author: Dongjoon Hyun <[email protected]>
AuthorDate: Wed Jul 15 14:30:46 2026 -0700
[SPARK-58153][CORE][R] Reject JAR entries escaping the extraction directory
in `RPackageUtils`
### What changes were proposed in this pull request?
This PR fixes a zip-slip (arbitrary file write) vulnerability in
`RPackageUtils.extractRFolder`, which derived its output path from a JAR entry
name without any containment check. An entry named `R/pkg/../../../../.bashrc`
satisfies `indexOf("R/pkg") == 0`, so the `../` sequences survived into the
path and `new File(tempDir, entryPath)` resolved outside `tempDir`.
The output path is now computed once, above the directory/file branch, and
validated before either branch uses it:
```scala
val outPath = new File(tempDir, entryPath).getCanonicalFile
if (!outPath.getCanonicalPath.startsWith(tempDir.getCanonicalPath +
File.separator)) {
throw new IOException(s"Malicious zip entry escaping target dir:
${entry.getName}")
}
```
### Why are the changes needed?
`extractRFolder` runs from `SparkSubmit` (via `checkAndBuildRPackage`) for
any `--jars` / `--packages` JAR whose manifest carries the `Spark-HasRPackage`
flag. Submitting a malicious JAR could write arbitrary files outside `tempDir`
on the submitting host — overwriting `~/.bashrc`, for example, escalates to
code execution.
### Does this PR introduce _any_ user-facing change?
- No. Well-formed R package JARs extract as before; only entries resolving
outside the extraction directory are now rejected.
- Note that `SparkR` is deprecated.
### How was this patch tested?
Pass the CIs with the newly added test case.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Claude Fable 5
Closes #57283 from dongjoon-hyun/SPARK-58153.
Authored-by: Dongjoon Hyun <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
(cherry picked from commit e9121bbf5a94b724b195a6f11c35a1a2d562e3d5)
Signed-off-by: Dongjoon Hyun <[email protected]>
---
.../org/apache/spark/deploy/RPackageUtils.scala | 10 +++++---
.../apache/spark/deploy/RPackageUtilsSuite.scala | 29 +++++++++++++++++++---
2 files changed, 32 insertions(+), 7 deletions(-)
diff --git a/core/src/main/scala/org/apache/spark/deploy/RPackageUtils.scala
b/core/src/main/scala/org/apache/spark/deploy/RPackageUtils.scala
index f14c2dd69397..29cddb76209f 100644
--- a/core/src/main/scala/org/apache/spark/deploy/RPackageUtils.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/RPackageUtils.scala
@@ -146,15 +146,17 @@ private[deploy] object RPackageUtils extends Logging {
val entryRIndex = entry.getName.indexOf(RJarEntries)
if (entryRIndex > -1) {
val entryPath = entry.getName.substring(entryRIndex)
+ val outPath = new File(tempDir, entryPath).getCanonicalFile
+ if (!outPath.getCanonicalPath.startsWith(tempDir.getCanonicalPath +
File.separator)) {
+ throw new IOException(s"Malicious zip entry escaping target dir:
${entry.getName}")
+ }
if (entry.isDirectory) {
- val dir = new File(tempDir, entryPath)
if (verbose) {
- print(log"Creating directory: ${MDC(PATH, dir)}", printStream)
+ print(log"Creating directory: ${MDC(PATH, outPath)}", printStream)
}
- Utils.createDirectory(dir)
+ Utils.createDirectory(outPath)
} else {
val inStream = jar.getInputStream(entry)
- val outPath = new File(tempDir, entryPath)
Utils.createParentDirs(outPath)
val outStream = new FileOutputStream(outPath)
if (verbose) {
diff --git
a/core/src/test/scala/org/apache/spark/deploy/RPackageUtilsSuite.scala
b/core/src/test/scala/org/apache/spark/deploy/RPackageUtilsSuite.scala
index 84e6b6971c27..da7b4bd960e3 100644
--- a/core/src/test/scala/org/apache/spark/deploy/RPackageUtilsSuite.scala
+++ b/core/src/test/scala/org/apache/spark/deploy/RPackageUtilsSuite.scala
@@ -17,11 +17,12 @@
package org.apache.spark.deploy
-import java.io.{File, OutputStream, PrintStream}
+import java.io.{File, FileOutputStream, IOException, OutputStream, PrintStream}
import java.net.URI
-import java.util.jar.{JarFile, Manifest}
+import java.nio.charset.StandardCharsets
+import java.util.jar.{JarFile, JarOutputStream, Manifest}
import java.util.jar.Attributes.Name
-import java.util.zip.ZipFile
+import java.util.zip.{ZipEntry, ZipFile}
import scala.collection.mutable.ArrayBuffer
import scala.jdk.CollectionConverters._
@@ -138,6 +139,28 @@ class RPackageUtilsSuite
}
}
+ test("SPARK-58153: jar entries escaping the extraction directory are
rejected") {
+ val tempDir = Utils.createTempDir()
+ Utils.tryWithSafeFinally {
+ val manifest = new Manifest
+ val attr = manifest.getMainAttributes
+ attr.put(Name.MANIFEST_VERSION, "1.0")
+ attr.put(new Name("Spark-HasRPackage"), "true")
+ val jar = new File(tempDir, "malicious.jar")
+ Utils.tryWithResource(new JarOutputStream(new FileOutputStream(jar),
manifest)) { out =>
+ out.putNextEntry(new ZipEntry("R/pkg/../../../../evil.txt"))
+ out.write("evil".getBytes(StandardCharsets.UTF_8))
+ out.closeEntry()
+ }
+ val e = intercept[IOException] {
+ RPackageUtils.checkAndBuildRPackage(jar.getAbsolutePath, new
BufferPrintStream)
+ }
+ assert(e.getMessage.contains("Malicious zip entry"))
+ } {
+ Utils.deleteRecursively(tempDir)
+ }
+ }
+
test("SparkR zipping works properly") {
val tempDir = Utils.createTempDir()
Utils.tryWithSafeFinally {
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
