chore: Added scout & trivy scan to github workflow (#37022)

## Description
Run trivy and scout scanner with image name


Fixes #`37036`  

## Automation

/ok-to-test tags="@tag.IDE"

### 🔍 Cypress test results
<!-- This is an auto-generated comment: Cypress test results  -->
> [!TIP]
> 🟢 🟢 🟢 All cypress tests have passed! 🎉 🎉 🎉
> Workflow run:
<https://github.com/appsmithorg/appsmith/actions/runs/11480586298>
> Commit: 5ebbcd37ec177c781d8b0be38a83ce695d211c9d
> <a
href="https://internal.appsmith.com/app/cypress-dashboard/rundetails-65890b3c81d7400d08fa9ee5?branch=master&workflowId=11480586298&attempt=1"
target="_blank">Cypress dashboard</a>.
> Tags: `@tag.IDE`
> Spec:
> <hr>Wed, 23 Oct 2024 13:36:44 UTC
<!-- end of auto-generated comment: Cypress test results  -->


## Communication
Should the DevRel and Marketing teams inform users about this change?
- [ ] Yes
- [x] No


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Introduced two new scripts for automated vulnerability scanning of
Docker images: `scout_vulnerabilities_data.sh` and
`trivy_vulnerabilities_data.sh`.
- Added a GitHub Actions workflow to automate vulnerability scanning and
update pull requests with results.

- **Bug Fixes**
- Improved error handling for missing environment variables in the new
scripts.

- **Documentation**
	- Added details on the new workflow and its steps for user reference.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
Sagar Khalasi 2024-10-23 20:01:40 +05:30 committed by GitHub
parent 9999c63aa1
commit 915b602dd5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 534 additions and 0 deletions

View File

@ -0,0 +1,143 @@
name: Run Vulnerability Data Script with Parameters and Update PR
on:
workflow_dispatch:
inputs:
image_name:
description: 'Docker image name to scan'
required: true
default: 'appsmith/appsmith-ce:release'
jobs:
run-and-update-pr:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: '20'
- name: Login to DockerHub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_HUB_USERNAME }}
password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
- name: Install pg
run: npm install pg
- name: Fetch vulnerability data
id: vulnerability_data
env:
DB_HOST: ${{ secrets.CYPRESS_DB_HOST }}
DB_NAME: ${{ secrets.CYPRESS_DB_NAME }}
DB_USER: ${{ secrets.CYPRESS_DB_USER }}
DB_PWD: ${{ secrets.CYPRESS_DB_PWD }}
uses: actions/github-script@v7
with:
script: |
const { Pool } = require("pg");
const fs = require('fs');
const path = require('path');
const { DB_HOST, DB_NAME, DB_USER, DB_PWD } = process.env;
const pool = new Pool({
user: DB_USER,
host: DB_HOST,
database: DB_NAME,
password: DB_PWD,
port: 5432,
connectionTimeoutMillis: 60000,
});
(async () => {
const client = await pool.connect();
try {
// Fetch vurn_id, product, scanner_tool, and priority from the database
const result = await client.query(`SELECT vurn_id, product, scanner_tool, priority FROM vulnerability_tracking`);
console.log('Vulnerability Data:', result.rows);
// Extract relevant fields from the result
const extractedData = result.rows.map(({ vurn_id, product, scanner_tool, priority }) => ({
vurn_id,
product,
scanner_tool,
priority
}));
console.log('Extracted Vulnerability Data:', extractedData);
// Prepare CSV content
const csvContent = [
['vurn_id', 'product', 'scanner_tool', 'priority'], // Add priority column header
...extractedData.map(row => [row.vurn_id, row.product, row.scanner_tool, row.priority])
]
.map(e => e.join(',')) // Join columns
.join('\n'); // Join rows
// Write to CSV file in workspace
const csvFilePath = path.join(process.env.GITHUB_WORKSPACE, 'vulnerability_base_data.csv');
fs.writeFileSync(csvFilePath, csvContent);
console.log(`Data successfully written to ${csvFilePath}`);
// Prepare TXT content
const txtContent = extractedData
.map(row => `vurn_id: ${row.vurn_id}, product: ${row.product}, scanner_tool: ${row.scanner_tool}, priority: ${row.priority}`)
.join('\n'); // Join rows
// Write to TXT file in workspace
const txtFilePath = path.join(process.env.GITHUB_WORKSPACE, 'vulnerability_base_data.txt');
fs.writeFileSync(txtFilePath, txtContent);
console.log(`Data successfully written to ${txtFilePath}`);
client.release();
return extractedData; // Return the extracted data
} catch (err) {
console.error('Error fetching vulnerability data:', err);
client.release();
}
})();
- name: Upload Vulnerability Data
uses: actions/upload-artifact@v3
with:
name: vulnerability-data
path: |
vulnerability_base_data.csv
vulnerability_base_data.txt
# Run Scout vulnerability data script
- name: Run Scout vulnerability data script
if: always()
env:
DB_HOST: ${{ secrets.CYPRESS_DB_HOST }}
DB_NAME: ${{ secrets.CYPRESS_DB_NAME }}
DB_USER: ${{ secrets.CYPRESS_DB_USER }}
DB_PWD: ${{ secrets.CYPRESS_DB_PWD }}
run: |
chmod +x scripts/scout_vulnerabilities_data.sh
./scripts/scout_vulnerabilities_data.sh \
"${{ inputs.image_name }}" \
"${{ github.event.pull_request.number }}" \
"${{ github.event.pull_request.html_url }}" \
"${{ github.run_id }}"
- name: Run Trivy vulnerability data script
if: always()
env:
DB_HOST: ${{ secrets.CYPRESS_DB_HOST }}
DB_NAME: ${{ secrets.CYPRESS_DB_NAME }}
DB_USER: ${{ secrets.CYPRESS_DB_USER }}
DB_PWD: ${{ secrets.CYPRESS_DB_PWD }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u "${{ github.actor }}" --password-stdin
chmod +x scripts/trivy_vulnerabilities_data.sh
./scripts/trivy_vulnerabilities_data.sh \
"${{ inputs.image_name }}" \
"${{ github.event.pull_request.number }}" \
"${{ github.event.pull_request.html_url }}" \
"${{ github.run_id }}"

View File

@ -0,0 +1,173 @@
#!/bin/bash
#Check required environment variables
required_vars=("DB_HOST" "DB_NAME" "DB_USER" "DB_PWD")
for var in "${required_vars[@]}"; do
if [ -z "${!var}" ] || [[ "${!var}" == "your_${var,,}" ]]; then
echo "Error: Required environment variable $var is missing or not set correctly."
exit 1
fi
done
DB_HOST="${DB_HOST}"
DB_NAME="${DB_NAME}"
DB_USER="${DB_USER}"
DB_PWD="${DB_PWD}"
# Assign the parameters from the workflow
IMAGE="$1"
GITHUB_PR_ID="$2"
GITHUB_PR_LINK="$3"
GITHUB_RUN_ID="$4"
OLD_VULN_FILE="${5:-vulnerability_base_data.csv}"
# Function to install Docker Scout
install_docker_scout() {
echo "Installing Docker Scout..."
local attempts=0
while [ $attempts -lt 3 ]; do
echo "Attempt $((attempts + 1))..."
curl -fsSL https://raw.githubusercontent.com/docker/scout-cli/main/install.sh -o install-scout.sh
sh install-scout.sh &> install_scout_log.txt
if [ $? -eq 0 ]; then
echo "Docker Scout installed successfully."
return 0
fi
echo "Attempt $((attempts + 1)) failed. Check install_scout_log.txt for details."
((attempts++))
sleep 2
done
echo "Error: Docker Scout installation failed after $attempts attempts."
exit 1
}
# Check if Docker is installed
if ! command -v docker &> /dev/null; then
echo "Error: Docker is not installed. Please install Docker and try again."
exit 1
fi
# Ensure Docker is running
if ! systemctl is-active --quiet docker; then
echo "Starting Docker..."
sudo systemctl start docker
fi
# Check if Docker Scout is installed
if ! command -v scout &> /dev/null; then
install_docker_scout
fi
# Prepare the output CSV file
CSV_OUTPUT_FILE="scout_vulnerabilities.csv"
rm -f "$CSV_OUTPUT_FILE"
# Extract the product name from the image name
case "$IMAGE" in
*appsmith/appsmith-ce:*) product_name="CE" ;;
*appsmith/appsmith-ee:*) product_name="EE" ;;
*appsmith/cloud-services:*) product_name="CLOUD" ;;
*) product_name="UNKNOWN" ;;
esac
# Fetch vulnerabilities and format the output correctly
docker scout cves "$IMAGE" | grep -E "✗ |CVE-" | awk -v product_name="$product_name" -F' ' '
{
# Check for valid vulnerability data and format it correctly
if ($2 != "" && $3 ~ /^CVE-/) {
# Extract severity level, CVE ID and format output correctly
print $3","product_name",""SCOUT"","$2
}
}' | sort -u > "$CSV_OUTPUT_FILE"
# Check if the CSV output file is empty
[ -s "$CSV_OUTPUT_FILE" ] || echo "No vulnerabilities found for image: $IMAGE" > "$CSV_OUTPUT_FILE"
# Compare new vulnerabilities against old vulnerabilities
echo "Comparing new vulnerabilities with existing vulnerabilities in $OLD_VULN_FILE..."
if [ -s "$OLD_VULN_FILE" ]; then
awk -F, 'NR==FNR {seen[$1","$2","$3","$4]; next} !($1","$2","$3","$4 in seen)' "$OLD_VULN_FILE" "$CSV_OUTPUT_FILE" > "scout_vulnerabilities_diff.csv"
else
echo "$OLD_VULN_FILE is empty. All new vulnerabilities will be included."
cp "$CSV_OUTPUT_FILE" "scout_vulnerabilities_diff.csv"
fi
# Output for verification
echo "Fetching passed data..."
cat "$OLD_VULN_FILE"
echo ""
echo "Fetching new data..."
cat "$CSV_OUTPUT_FILE"
echo ""
echo "Fetching diff..."
cat "scout_vulnerabilities_diff.csv"
echo ""
# Insert new vulnerabilities into the PostgreSQL database using psql
insert_vulns_into_db() {
local count=0
local query_file="insert_vulns.sql"
echo "BEGIN;" > "$query_file" # Start the transaction
# Create an associative array to hold existing entries from the database
declare -A existing_entries
# Fetch existing vulnerabilities from the database to avoid duplicates
psql -t -c "SELECT vurn_id, product, scanner_tool, priority FROM vulnerability_tracking WHERE scanner_tool = 'SCOUT'" "postgresql://$DB_USER:$DB_PWD@$DB_HOST/$DB_NAME" | while IFS='|' read -r db_vurn_id db_product db_scanner_tool db_priority; do
existing_entries["$db_product,$db_scanner_tool,$db_vurn_id"]="$db_priority"
done
while IFS=, read -r vurn_id product scanner_tool priority; do
# Skip empty lines
if [[ -z "$vurn_id" || -z "$priority" || -z "$product" || -z "$scanner_tool" ]]; then
echo "Skipping empty vulnerability entry"
continue
fi
# Check if the entry already exists
if [[ -n "${existing_entries["$product,$scanner_tool,$vurn_id"]}" ]]; then
echo "Entry for $vurn_id already exists in the database. Skipping."
continue
fi
local pr_id="$GITHUB_PR_ID"
local pr_link="$GITHUB_PR_LINK"
local created_date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
local update_date="$created_date"
local comments="Initial vulnerability report"
local owner="John Doe"
local pod="Security"
# Escape single quotes in vulnerability ID, product, and priority
vurn_id=$(echo "$vurn_id" | sed "s/'/''/g")
priority=$(echo "$priority" | sed "s/'/''/g")
product=$(echo "$product" | sed "s/'/''/g")
scanner_tool=$(echo "$scanner_tool" | sed "s/'/''/g")
# Write each insert query to the SQL file
echo "INSERT INTO vulnerability_tracking (product, scanner_tool, vurn_id, priority, pr_id, pr_link, github_run_id, created_date, update_date, comments, owner, pod) VALUES ('$product', '$scanner_tool', '$vurn_id', '$priority', '$pr_id', '$pr_link', '$GITHUB_RUN_ID', '$created_date', '$update_date', '$comments', '$owner', '$pod');" >> "$query_file"
((count++))
done < "scout_vulnerabilities_diff.csv"
echo "COMMIT;" >> "$query_file" # End the transaction
echo "Queries written to $query_file."
# Execute the SQL file
psql -e "postgresql://$DB_USER:$DB_PWD@$DB_HOST/$DB_NAME" -f "$query_file"
# Check if the execution was successful
if [ $? -eq 0 ]; then
echo "Vulnerabilities successfully inserted into the database."
else
echo "Error: Failed to insert vulnerabilities. Please check the database connection or query."
exit 1
fi
}
# Call the function to generate the insert queries and execute them
if [ -s "scout_vulnerabilities_diff.csv" ]; then
insert_vulns_into_db
else
echo "No new vulnerabilities to insert."
fi

View File

@ -0,0 +1,218 @@
#!/bin/bash
#Check required environment variables
required_vars=("DB_HOST" "DB_NAME" "DB_USER" "DB_PWD")
for var in "${required_vars[@]}"; do
if [ -z "${!var}" ] || [[ "${!var}" == "your_${var,,}" ]]; then
echo "Error: Required environment variable $var is missing or not set correctly."
exit 1
fi
done
DB_HOST="${DB_HOST}"
DB_NAME="${DB_NAME}"
DB_USER="${DB_USER}"
DB_PWD="${DB_PWD}"
# Assign the parameters from the workflow
IMAGE="$1"
GITHUB_PR_ID="$2"
GITHUB_PR_LINK="$3"
GITHUB_RUN_ID="$4"
OLD_VULN_FILE="${5:-vulnerability_base_data.csv}"
# Define the maximum number of retries
MAX_RETRIES=3
# Function to install Trivy with retry logic
install_trivy_with_retry() {
local count=0
local success=false
while [[ $count -lt $MAX_RETRIES ]]; do
echo "Attempting to install Trivy (attempt $((count + 1)))..."
# Fetch the latest release dynamically instead of hardcoding
TRIVY_VERSION=$(curl -s https://api.github.com/repos/aquasecurity/trivy/releases/latest | grep '"tag_name"' | sed -E 's/.*"v([^"]+)".*/\1/')
TRIVY_URL="https://github.com/aquasecurity/trivy/releases/download/v$TRIVY_VERSION/trivy_"$TRIVY_VERSION"_Linux-64bit.tar.gz"
echo "Attempting to install $TRIVY_VERSION from $TRIVY_URL"
# Download and extract Trivy
curl -sfL "$TRIVY_URL" | tar -xzf - trivy
# Check if extraction was successful
if [[ $? -eq 0 ]]; then
# Create a local bin directory if it doesn't exist
mkdir -p "$HOME/bin"
# Move Trivy to the local bin directory
mv trivy "$HOME/bin/"
# Manually add the bin directory to PATH for this session
export PATH="$HOME/bin:$PATH"
# Check if Trivy is successfully installed
if command -v trivy &> /dev/null; then
success=true
break
fi
fi
echo "Trivy installation failed. Retrying..."
count=$((count + 1))
done
if [[ $success = false ]]; then
echo "Error: Trivy installation failed after $MAX_RETRIES attempts."
exit 1
fi
echo "Trivy installed successfully."
}
# Check if Trivy is installed, if not, install it with retry logic
if ! command -v trivy &> /dev/null; then
install_trivy_with_retry
fi
NEW_VULN_FILE="trivy_vulnerabilities_new.csv"
DIFF_OUTPUT_FILE="trivy_vulnerabilities_diff.csv"
rm -f "$NEW_VULN_FILE" "$DIFF_OUTPUT_FILE"
touch "$OLD_VULN_FILE"
# Extract the product name from the image name
case "$IMAGE" in
*appsmith/appsmith-ce:*) product_name="CE" ;;
*appsmith/appsmith-ee:*) product_name="EE" ;;
*appsmith/cloud-services:*) product_name="CLOUD" ;;
*) product_name="UNKNOWN" ;;
esac
# Function to run Trivy scan
run_trivy_scan() {
echo "Cleaning up Trivy data..."
trivy clean --all
echo "Running Trivy scan for image: $IMAGE..."
if ! trivy image \
--db-repository public.ecr.aws/aquasecurity/trivy-db \
--java-db-repository public.ecr.aws/aquasecurity/trivy-java-db \
--insecure \
--format json \
"$IMAGE" > "trivy_vulnerabilities.json"; then
echo "Error: Trivy is not available or the image does not exist."
exit 1
fi
}
# Call the function to run the scan
run_trivy_scan
# Process vulnerabilities and generate the desired CSV format
if jq -e '.Results | length > 0' "trivy_vulnerabilities.json" > /dev/null; then
jq -r --arg product "$product_name" '.Results[].Vulnerabilities[] | "\(.VulnerabilityID),\($product),TRIVY,\(.Severity)"' "trivy_vulnerabilities.json" | sed 's/^\s*//;s/\s*$//' | sort -u > "$NEW_VULN_FILE"
echo "Vulnerabilities saved to $NEW_VULN_FILE"
else
echo "No vulnerabilities found for image: $IMAGE"
echo "No vulnerabilities found." > "$NEW_VULN_FILE"
fi
# Compare new vulnerabilities with the old file
if [ -s "$NEW_VULN_FILE" ]; then
sort "$OLD_VULN_FILE" -o "$OLD_VULN_FILE" # Sort the old vulnerabilities file
sort "$NEW_VULN_FILE" -o "$NEW_VULN_FILE" # Sort the new vulnerabilities file
# Get the difference between new and old vulnerabilities
comm -13 "$OLD_VULN_FILE" "$NEW_VULN_FILE" > "$DIFF_OUTPUT_FILE"
if [ -s "$DIFF_OUTPUT_FILE" ]; then
echo "New vulnerabilities found and recorded in $DIFF_OUTPUT_FILE."
else
echo "No new vulnerabilities found for image: $IMAGE."
fi
else
echo "No new vulnerabilities found for image: $IMAGE."
fi
# Cleanup JSON file
rm -f "trivy_vulnerabilities.json"
# Output for verification
echo "Fetching passed data..."
cat "$OLD_VULN_FILE"
echo ""
echo "Fetching new data..."
cat "$NEW_VULN_FILE"
echo ""
echo "Fetching diff..."
cat $DIFF_OUTPUT_FILE
echo ""
# Insert new vulnerabilities into the PostgreSQL database using psql
insert_vulns_into_db() {
local count=0
local query_file="insert_vulns.sql"
echo "BEGIN;" > "$query_file" # Start the transaction
# Create an associative array to hold existing entries from the database
declare -A existing_entries
# Fetch existing vulnerabilities from the database to avoid duplicates
psql -t -c "SELECT vurn_id, product, scanner_tool, priority FROM vulnerability_tracking WHERE scanner_tool = 'TRIVY'" "postgresql://$DB_USER:$DB_PWD@$DB_HOST/$DB_NAME" | while IFS='|' read -r db_vurn_id db_product db_scanner_tool db_priority; do
existing_entries["$db_product,$db_scanner_tool,$db_vurn_id"]="$db_priority"
done
while IFS=, read -r vurn_id product scanner_tool priority; do
# Skip empty lines
if [[ -z "$vurn_id" || -z "$priority" || -z "$product" || -z "$scanner_tool" ]]; then
echo "Skipping empty vulnerability entry"
continue
fi
# Check if the entry already exists
if [[ -n "${existing_entries["$product,$scanner_tool,$vurn_id"]}" ]]; then
echo "Entry for $vurn_id already exists in the database. Skipping."
continue
fi
local pr_id="$GITHUB_PR_ID"
local pr_link="$GITHUB_PR_LINK"
local created_date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
local update_date="$created_date"
local comments="Initial vulnerability report"
local owner="John Doe"
local pod="Security"
# Escape single quotes in vulnerability ID, product, and priority
vurn_id=$(echo "$vurn_id" | sed "s/'/''/g")
priority=$(echo "$priority" | sed "s/'/''/g")
product=$(echo "$product" | sed "s/'/''/g")
scanner_tool=$(echo "$scanner_tool" | sed "s/'/''/g")
# Write each insert query to the SQL file
echo "INSERT INTO vulnerability_tracking (product, scanner_tool, vurn_id, priority, pr_id, pr_link, github_run_id, created_date, update_date, comments, owner, pod) VALUES ('$product', '$scanner_tool', '$vurn_id', '$priority', '$pr_id', '$pr_link', '$GITHUB_RUN_ID', '$created_date', '$update_date', '$comments', '$owner', '$pod');" >> "$query_file"
((count++))
done < $DIFF_OUTPUT_FILE
echo "COMMIT;" >> "$query_file" # End the transaction
echo "Queries written to $query_file."
# Execute the SQL file
psql -e "postgresql://$DB_USER:$DB_PWD@$DB_HOST/$DB_NAME" -f "$query_file"
# Check if the execution was successful
if [ $? -eq 0 ]; then
echo "Vulnerabilities successfully inserted into the database."
else
echo "Error: Failed to insert vulnerabilities. Please check the database connection or query."
exit 1
fi
}
# Call the function to generate the insert queries and execute them
if [ -s $DIFF_OUTPUT_FILE ]; then
insert_vulns_into_db
else
echo "No new vulnerabilities to insert."
fi