mirror of
https://github.com/freedomofpress/dangerzone.git
synced 2025-04-28 18:02:38 +02:00
f03bc71855
This wraps the existing container image inside a gVisor-based sandbox. gVisor is an open-source OCI-compliant container runtime. It is a userspace reimplementation of the Linux kernel in a memory-safe language. It works by creating a sandboxed environment in which regular Linux applications run, but their system calls are intercepted by gVisor. gVisor then redirects these system calls and reinterprets them in its own kernel. This means the host Linux kernel is isolated from the sandboxed application, thereby providing protection against Linux container escape attacks. It also uses `seccomp-bpf` to provide a secondary layer of defense against container escapes. Even if its userspace kernel gets compromised, attackers would have to additionally have a Linux container escape vector, and that exploit would have to fit within the restricted `seccomp-bpf` rules that gVisor adds on itself. Fixes #126 Fixes #224 Fixes #225 Fixes #228
116 lines
4.4 KiB
Docker
116 lines
4.4 KiB
Docker
###########################################
|
|
# Build PyMuPDF
|
|
|
|
FROM alpine:latest as pymupdf-build
|
|
|
|
ARG REQUIREMENTS_TXT
|
|
|
|
# Install PyMuPDF via hash-checked requirements file
|
|
COPY ${REQUIREMENTS_TXT} /tmp/requirements.txt
|
|
RUN apk --no-cache add linux-headers g++ linux-headers gcc make python3-dev py3-pip clang-dev
|
|
RUN pip install -vv --break-system-packages --require-hashes -r /tmp/requirements.txt
|
|
|
|
|
|
###########################################
|
|
# Download Tesseract data
|
|
|
|
FROM alpine:latest as tessdata-dl
|
|
ARG TESSDATA_CHECKSUM=d0e3bb6f3b4e75748680524a1d116f2bfb145618f8ceed55b279d15098a530f9
|
|
|
|
# Download the trained models from the latest GitHub release of Tesseract, and
|
|
# store them under /usr/share/tessdata. This is basically what distro packages
|
|
# do under the hood.
|
|
#
|
|
# Because the GitHub release contains more files than just the trained models,
|
|
# we use `find` to fetch only the '*.traineddata' files in the top directory.
|
|
#
|
|
# Before we untar the models, we also check if the checksum is the expected one.
|
|
RUN mkdir /usr/share/tessdata/ && mkdir tessdata && cd tessdata \
|
|
&& TESSDATA_VERSION=$(wget -O- -nv https://api.github.com/repos/tesseract-ocr/tessdata_fast/releases/latest \
|
|
| sed -n 's/^.*"tag_name": "\([0-9.]\+\)".*$/\1/p') \
|
|
&& wget https://github.com/tesseract-ocr/tessdata_fast/archive/$TESSDATA_VERSION/tessdata_fast-$TESSDATA_VERSION.tar.gz \
|
|
&& echo "$TESSDATA_CHECKSUM tessdata_fast-$TESSDATA_VERSION.tar.gz" | sha256sum -c \
|
|
&& tar -xzvf tessdata_fast-$TESSDATA_VERSION.tar.gz -C . \
|
|
&& find . -name '*.traineddata' -maxdepth 2 -exec cp {} /usr/share/tessdata/ \; \
|
|
&& cd .. && rm -r tessdata
|
|
|
|
|
|
###########################################
|
|
# Download H2ORestart
|
|
FROM alpine:latest as h2orestart-dl
|
|
ARG H2ORESTART_CHECKSUM=5db816a1e57b510456633f55e693cb5ef3675ef8b35df4f31c90ab9d4c66071a
|
|
RUN mkdir /libreoffice_ext && cd libreoffice_ext \
|
|
&& H2ORESTART_FILENAME=h2orestart.oxt \
|
|
&& H2ORESTART_VERSION="v0.5.7" \
|
|
&& wget https://github.com/ebandal/H2Orestart/releases/download/$H2ORESTART_VERSION/$H2ORESTART_FILENAME \
|
|
&& echo "$H2ORESTART_CHECKSUM $H2ORESTART_FILENAME" | sha256sum -c \
|
|
&& install -dm777 "/usr/lib/libreoffice/share/extensions/"
|
|
|
|
|
|
###########################################
|
|
# Dangerzone image
|
|
|
|
FROM alpine:latest AS dangerzone-image
|
|
|
|
# Install dependencies
|
|
RUN apk --no-cache -U upgrade && \
|
|
apk --no-cache add \
|
|
libreoffice \
|
|
openjdk8 \
|
|
python3 \
|
|
py3-magic \
|
|
font-noto-cjk
|
|
|
|
COPY --from=pymupdf-build /usr/lib/python3.12/site-packages/fitz/ /usr/lib/python3.12/site-packages/fitz
|
|
COPY --from=pymupdf-build /usr/lib/python3.12/site-packages/pymupdf/ /usr/lib/python3.12/site-packages/pymupdf
|
|
COPY --from=tessdata-dl /usr/share/tessdata/ /usr/share/tessdata
|
|
COPY --from=h2orestart-dl /libreoffice_ext/ /libreoffice_ext
|
|
|
|
RUN install -dm777 "/usr/lib/libreoffice/share/extensions/"
|
|
|
|
RUN mkdir -p /opt/dangerzone/dangerzone
|
|
RUN touch /opt/dangerzone/dangerzone/__init__.py
|
|
COPY conversion /opt/dangerzone/dangerzone/conversion
|
|
|
|
# Add the unprivileged user. Set the UID/GID of the dangerzone user/group to
|
|
# 1000, since we will point to it from the OCI config.
|
|
#
|
|
# NOTE: A tmpfs will be mounted over /home/dangerzone directory,
|
|
# so nothing within it from the image will be persisted.
|
|
RUN addgroup -g 1000 dangerzone && \
|
|
adduser -u 1000 -s /bin/true -G dangerzone -h /home/dangerzone -D dangerzone
|
|
|
|
###########################################
|
|
# gVisor wrapper image
|
|
|
|
FROM alpine:latest
|
|
|
|
RUN apk --no-cache -U upgrade && \
|
|
apk --no-cache add python3
|
|
|
|
RUN GVISOR_URL="https://storage.googleapis.com/gvisor/releases/release/latest/$(uname -m)"; \
|
|
wget "${GVISOR_URL}/runsc" "${GVISOR_URL}/runsc.sha512" && \
|
|
sha512sum -c runsc.sha512 && \
|
|
rm -f runsc.sha512 && \
|
|
chmod 555 runsc && \
|
|
mv runsc /usr/bin/
|
|
|
|
# Add the unprivileged `dangerzone` user.
|
|
RUN addgroup dangerzone && \
|
|
adduser -s /bin/true -G dangerzone -h /home/dangerzone -D dangerzone
|
|
|
|
# Switch to the dangerzone user for the rest of the script.
|
|
USER dangerzone
|
|
|
|
# Copy the Dangerzone image, as created by the previous steps, into the home
|
|
# directory of the `dangerzone` user.
|
|
RUN mkdir /home/dangerzone/dangerzone-image
|
|
COPY --from=dangerzone-image / /home/dangerzone/dangerzone-image/rootfs
|
|
|
|
# Create a directory that will be used by gVisor as the place where it will
|
|
# store the state of its containers.
|
|
RUN mkdir /home/dangerzone/.containers
|
|
|
|
COPY gvisor_wrapper/entrypoint.py /
|
|
|
|
ENTRYPOINT ["/entrypoint.py"]
|