From 237f8a11e11fdcc793a09e787e48215676d9b95b Mon Sep 17 00:00:00 2001
From: Matan Yemini <50515643+MatanYemini@users.noreply.github.com>
Date: Tue, 29 Apr 2025 22:07:00 +0300
Subject: [PATCH] feat: add common package registries domains to
 allowed-domains list (#414)

feat: add common package registries domains to allowed-domains list
---
 codex-cli/scripts/init_firewall.sh    | 25 ++++++++++++++++++++---
 codex-cli/scripts/run_in_container.sh | 29 +++++++++++++++++++++++++--
 2 files changed, 49 insertions(+), 5 deletions(-)

diff --git a/codex-cli/scripts/init_firewall.sh b/codex-cli/scripts/init_firewall.sh
index 6e0fa438..1251325f 100644
--- a/codex-cli/scripts/init_firewall.sh
+++ b/codex-cli/scripts/init_firewall.sh
@@ -2,6 +2,26 @@
 set -euo pipefail  # Exit on error, undefined vars, and pipeline failures
 IFS=$'\n\t'       # Stricter word splitting
 
+# Read allowed domains from file
+ALLOWED_DOMAINS_FILE="/etc/codex/allowed_domains.txt"
+if [ -f "$ALLOWED_DOMAINS_FILE" ]; then
+    ALLOWED_DOMAINS=()
+    while IFS= read -r domain; do
+        ALLOWED_DOMAINS+=("$domain")
+    done < "$ALLOWED_DOMAINS_FILE"
+    echo "Using domains from file: ${ALLOWED_DOMAINS[*]}"
+else
+    # Fallback to default domains
+    ALLOWED_DOMAINS=("api.openai.com")
+    echo "Domains file not found, using default: ${ALLOWED_DOMAINS[*]}"
+fi
+
+# Ensure we have at least one domain
+if [ ${#ALLOWED_DOMAINS[@]} -eq 0 ]; then
+    echo "ERROR: No allowed domains specified"
+    exit 1
+fi
+
 # Flush existing rules and delete existing ipsets
 iptables -F
 iptables -X
@@ -24,8 +44,7 @@ iptables -A OUTPUT -o lo -j ACCEPT
 ipset create allowed-domains hash:net
 
 # Resolve and add other allowed domains
-for domain in \
-    "api.openai.com"; do
+for domain in "${ALLOWED_DOMAINS[@]}"; do
     echo "Resolving $domain..."
     ips=$(dig +short A "$domain")
     if [ -z "$ips" ]; then
@@ -87,7 +106,7 @@ else
     echo "Firewall verification passed - unable to reach https://example.com as expected"
 fi
 
-# Verify OpenAI API access
+# Always verify OpenAI API access is working
 if ! curl --connect-timeout 5 https://api.openai.com >/dev/null 2>&1; then
     echo "ERROR: Firewall verification failed - unable to reach https://api.openai.com"
     exit 1
diff --git a/codex-cli/scripts/run_in_container.sh b/codex-cli/scripts/run_in_container.sh
index 1da286a7..01070cf0 100755
--- a/codex-cli/scripts/run_in_container.sh
+++ b/codex-cli/scripts/run_in_container.sh
@@ -10,6 +10,8 @@ set -e
 
 # Default the work directory to WORKSPACE_ROOT_DIR if not provided.
 WORK_DIR="${WORKSPACE_ROOT_DIR:-$(pwd)}"
+# Default allowed domains - can be overridden with OPENAI_ALLOWED_DOMAINS env var
+OPENAI_ALLOWED_DOMAINS="${OPENAI_ALLOWED_DOMAINS:-api.openai.com}"
 
 # Parse optional flag.
 if [ "$1" = "--work_dir" ]; then
@@ -45,6 +47,12 @@ if [ -z "$WORK_DIR" ]; then
   exit 1
 fi
 
+# Verify that OPENAI_ALLOWED_DOMAINS is not empty
+if [ -z "$OPENAI_ALLOWED_DOMAINS" ]; then
+  echo "Error: OPENAI_ALLOWED_DOMAINS is empty."
+  exit 1
+fi
+
 # Kill any existing container for the working directory using cleanup(), centralizing removal logic.
 cleanup
 
@@ -57,8 +65,25 @@ docker run --name "$CONTAINER_NAME" -d \
   codex \
   sleep infinity
 
-# Initialize the firewall inside the container with root privileges.
-docker exec --user root "$CONTAINER_NAME" /usr/local/bin/init_firewall.sh
+# Write the allowed domains to a file in the container
+docker exec --user root "$CONTAINER_NAME" bash -c "mkdir -p /etc/codex"
+for domain in $OPENAI_ALLOWED_DOMAINS; do
+  # Validate domain format to prevent injection
+  if [[ ! "$domain" =~ ^[a-zA-Z0-9][a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$ ]]; then
+    echo "Error: Invalid domain format: $domain"
+    exit 1
+  fi
+  echo "$domain" | docker exec --user root -i "$CONTAINER_NAME" bash -c "cat >> /etc/codex/allowed_domains.txt"
+done
+
+# Set proper permissions on the domains file
+docker exec --user root "$CONTAINER_NAME" bash -c "chmod 444 /etc/codex/allowed_domains.txt && chown root:root /etc/codex/allowed_domains.txt"
+
+# Initialize the firewall inside the container as root user
+docker exec --user root "$CONTAINER_NAME" bash -c "/usr/local/bin/init_firewall.sh"
+
+# Remove the firewall script after running it
+docker exec --user root "$CONTAINER_NAME" bash -c "rm -f /usr/local/bin/init_firewall.sh"
 
 # Execute the provided command in the container, ensuring it runs in the work directory.
 # We use a parameterized bash command to safely handle the command and directory.