url fixes for access issues (#4013)

# Description of Changes


This pull request introduces a new SSRF (Server-Side Request Forgery)
protection mechanism for URL handling in the application. Key changes
include adding a dedicated `SsrfProtectionService`, integrating
SSRF-safe policies into HTML sanitization, and extending application
settings to support configurable URL security options.

### SSRF Protection Implementation:
* **`SsrfProtectionService`**: Added a new service to handle SSRF
protection with configurable levels (`OFF`, `MEDIUM`, `MAX`) and checks
for private networks, localhost, link-local addresses, and cloud
metadata endpoints
(`app/common/src/main/java/stirling/software/common/service/SsrfProtectionService.java`).

### Application Configuration Enhancements:
* **`ApplicationProperties`**: Introduced a new `Html` configuration
class with nested `UrlSecurity` settings, allowing fine-grained control
over URL security, including allowed/blocked domains and internal TLDs
(`app/common/src/main/java/stirling/software/common/model/ApplicationProperties.java`).
[[1]](diffhunk://#diff-1c357db0a3e88cf5bedd4a5852415fadad83b8b3b9eb56e67059d8b9d8b10702R293)
[[2]](diffhunk://#diff-1c357db0a3e88cf5bedd4a5852415fadad83b8b3b9eb56e67059d8b9d8b10702R346-R364)
* **`settings.yml.template`**: Updated the configuration template to
include the new `html.urlSecurity` settings, enabling users to customize
SSRF protection behavior
(`app/core/src/main/resources/settings.yml.template`).

### HTML Sanitization Updates:
* **`CustomHtmlSanitizer`**: Integrated SSRF-safe URL validation into
the HTML sanitizer by using the `SsrfProtectionService`. Added a custom
policy for validating `img` tags' `src` attributes
(`app/common/src/main/java/stirling/software/common/util/CustomHtmlSanitizer.java`).

---

## Checklist

### General

- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md)
(if applicable)
- [ ] I have performed a self-review of my own code
- [ ] My changes generate no new warnings

### Documentation

- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
(if functionality has heavily changed)
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)

### UI Changes (if applicable)

- [ ] Screenshots or videos demonstrating the UI changes are attached
(e.g., as comments or direct attachments in the PR)

### Testing (if applicable)

- [ ] I have tested my changes locally. Refer to the [Testing
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing)
for more details.

---------

Co-authored-by: a <a>
Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Anthony Stirling
2025-07-24 13:53:21 +01:00
committed by GitHub
parent c161000f85
commit 7d6b70871b
14 changed files with 462 additions and 84 deletions

View File

@@ -290,6 +290,7 @@ public class ApplicationProperties {
private Datasource datasource;
private Boolean disableSanitize;
private Boolean enableUrlToPDF;
private Html html = new Html();
private CustomPaths customPaths = new CustomPaths();
private String fileUploadLimit;
private TempFileManagement tempFileManagement = new TempFileManagement();
@@ -342,6 +343,25 @@ public class ApplicationProperties {
}
}
@Data
public static class Html {
private UrlSecurity urlSecurity = new UrlSecurity();
@Data
public static class UrlSecurity {
private boolean enabled = true;
private String level = "MEDIUM"; // MAX, MEDIUM, OFF
private List<String> allowedDomains = new ArrayList<>();
private List<String> blockedDomains = new ArrayList<>();
private List<String> internalTlds =
Arrays.asList(".local", ".internal", ".corp", ".home");
private boolean blockPrivateNetworks = true;
private boolean blockLocalhost = true;
private boolean blockLinkLocal = true;
private boolean blockCloudMetadata = true;
}
}
@Data
public static class Datasource {
private boolean enableCustomDatabase;

View File

@@ -0,0 +1,208 @@
package stirling.software.common.service;
import java.net.InetAddress;
import java.net.URI;
import java.net.UnknownHostException;
import java.util.regex.Pattern;
import org.springframework.stereotype.Service;
import lombok.RequiredArgsConstructor;
import lombok.extern.slf4j.Slf4j;
import stirling.software.common.model.ApplicationProperties;
@Service
@RequiredArgsConstructor
@Slf4j
public class SsrfProtectionService {
private final ApplicationProperties applicationProperties;
private static final Pattern DATA_URL_PATTERN =
Pattern.compile("^data:.*", Pattern.CASE_INSENSITIVE);
private static final Pattern FRAGMENT_PATTERN = Pattern.compile("^#.*");
public enum SsrfProtectionLevel {
OFF, // No SSRF protection - allows all URLs
MEDIUM, // Block internal networks but allow external URLs
MAX // Block all external URLs - only data: and fragments
}
public boolean isUrlAllowed(String url) {
ApplicationProperties.Html.UrlSecurity config =
applicationProperties.getSystem().getHtml().getUrlSecurity();
if (!config.isEnabled()) {
return true;
}
if (url == null || url.trim().isEmpty()) {
return false;
}
String trimmedUrl = url.trim();
// Always allow data URLs and fragments
if (DATA_URL_PATTERN.matcher(trimmedUrl).matches()
|| FRAGMENT_PATTERN.matcher(trimmedUrl).matches()) {
return true;
}
SsrfProtectionLevel level = parseProtectionLevel(config.getLevel());
switch (level) {
case OFF:
return true;
case MAX:
return isMaxSecurityAllowed(trimmedUrl, config);
case MEDIUM:
return isMediumSecurityAllowed(trimmedUrl, config);
default:
return false;
}
}
private SsrfProtectionLevel parseProtectionLevel(String level) {
try {
return SsrfProtectionLevel.valueOf(level.toUpperCase());
} catch (IllegalArgumentException e) {
log.warn("Invalid SSRF protection level '{}', defaulting to MEDIUM", level);
return SsrfProtectionLevel.MEDIUM;
}
}
private boolean isMaxSecurityAllowed(
String url, ApplicationProperties.Html.UrlSecurity config) {
// MAX security: only allow explicitly whitelisted domains
try {
URI uri = new URI(url);
String host = uri.getHost();
if (host == null) {
return false;
}
return config.getAllowedDomains().contains(host.toLowerCase());
} catch (Exception e) {
log.debug("Failed to parse URL for MAX security check: {}", url, e);
return false;
}
}
private boolean isMediumSecurityAllowed(
String url, ApplicationProperties.Html.UrlSecurity config) {
try {
URI uri = new URI(url);
String host = uri.getHost();
if (host == null) {
return false;
}
String hostLower = host.toLowerCase();
// Check explicit blocked domains
if (config.getBlockedDomains().contains(hostLower)) {
log.debug("URL blocked by explicit domain blocklist: {}", url);
return false;
}
// Check internal TLD patterns
for (String tld : config.getInternalTlds()) {
if (hostLower.endsWith(tld.toLowerCase())) {
log.debug("URL blocked by internal TLD pattern '{}': {}", tld, url);
return false;
}
}
// If allowedDomains is specified, only allow those
if (!config.getAllowedDomains().isEmpty()) {
boolean isAllowed =
config.getAllowedDomains().stream()
.anyMatch(
domain ->
hostLower.equals(domain.toLowerCase())
|| hostLower.endsWith(
"." + domain.toLowerCase()));
if (!isAllowed) {
log.debug("URL not in allowed domains list: {}", url);
return false;
}
}
// Resolve hostname to IP address for network-based checks
try {
InetAddress address = InetAddress.getByName(host);
if (config.isBlockPrivateNetworks() && isPrivateAddress(address)) {
log.debug("URL blocked - private network address: {}", url);
return false;
}
if (config.isBlockLocalhost() && address.isLoopbackAddress()) {
log.debug("URL blocked - localhost address: {}", url);
return false;
}
if (config.isBlockLinkLocal() && address.isLinkLocalAddress()) {
log.debug("URL blocked - link-local address: {}", url);
return false;
}
if (config.isBlockCloudMetadata()
&& isCloudMetadataAddress(address.getHostAddress())) {
log.debug("URL blocked - cloud metadata endpoint: {}", url);
return false;
}
} catch (UnknownHostException e) {
log.debug("Failed to resolve hostname for SSRF check: {}", host, e);
return false;
}
return true;
} catch (Exception e) {
log.debug("Failed to parse URL for MEDIUM security check: {}", url, e);
return false;
}
}
private boolean isPrivateAddress(InetAddress address) {
return address.isSiteLocalAddress()
|| address.isAnyLocalAddress()
|| isPrivateIPv4Range(address.getHostAddress());
}
private boolean isPrivateIPv4Range(String ip) {
return ip.startsWith("10.")
|| ip.startsWith("192.168.")
|| (ip.startsWith("172.") && isInRange172(ip))
|| ip.startsWith("127.")
|| "0.0.0.0".equals(ip);
}
private boolean isInRange172(String ip) {
String[] parts = ip.split("\\.");
if (parts.length >= 2) {
try {
int secondOctet = Integer.parseInt(parts[1]);
return secondOctet >= 16 && secondOctet <= 31;
} catch (NumberFormatException e) {
return false;
}
}
return false;
}
private boolean isCloudMetadataAddress(String ip) {
// Cloud metadata endpoints for AWS, GCP, Azure, Oracle Cloud, and IBM Cloud
return ip.startsWith("169.254.169.254") // AWS/GCP/Azure
|| ip.startsWith("fd00:ec2::254") // AWS IPv6
|| ip.startsWith("169.254.169.253") // Oracle Cloud
|| ip.startsWith("169.254.169.250"); // IBM Cloud
}
}

View File

@@ -1,21 +1,71 @@
package stirling.software.common.util;
import org.owasp.html.AttributePolicy;
import org.owasp.html.HtmlPolicyBuilder;
import org.owasp.html.PolicyFactory;
import org.owasp.html.Sanitizers;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Component;
import stirling.software.common.model.ApplicationProperties;
import stirling.software.common.service.SsrfProtectionService;
@Component
public class CustomHtmlSanitizer {
private static final PolicyFactory POLICY =
private final SsrfProtectionService ssrfProtectionService;
private final ApplicationProperties applicationProperties;
@Autowired
public CustomHtmlSanitizer(
SsrfProtectionService ssrfProtectionService,
ApplicationProperties applicationProperties) {
this.ssrfProtectionService = ssrfProtectionService;
this.applicationProperties = applicationProperties;
}
private final AttributePolicy SSRF_SAFE_URL_POLICY =
new AttributePolicy() {
@Override
public String apply(String elementName, String attributeName, String value) {
if (value == null || value.trim().isEmpty()) {
return null;
}
String trimmedValue = value.trim();
// Use the SSRF protection service to validate the URL
if (ssrfProtectionService != null
&& !ssrfProtectionService.isUrlAllowed(trimmedValue)) {
return null;
}
return trimmedValue;
}
};
private final PolicyFactory SSRF_SAFE_IMAGES_POLICY =
new HtmlPolicyBuilder()
.allowElements("img")
.allowAttributes("alt", "width", "height", "title")
.onElements("img")
.allowAttributes("src")
.matching(SSRF_SAFE_URL_POLICY)
.onElements("img")
.toFactory();
private final PolicyFactory POLICY =
Sanitizers.FORMATTING
.and(Sanitizers.BLOCKS)
.and(Sanitizers.STYLES)
.and(Sanitizers.LINKS)
.and(Sanitizers.TABLES)
.and(Sanitizers.IMAGES)
.and(SSRF_SAFE_IMAGES_POLICY)
.and(new HtmlPolicyBuilder().disallowElements("noscript").toFactory());
public static String sanitize(String html) {
String htmlAfter = POLICY.sanitize(html);
return htmlAfter;
public String sanitize(String html) {
boolean disableSanitize =
Boolean.TRUE.equals(applicationProperties.getSystem().getDisableSanitize());
return disableSanitize ? html : POLICY.sanitize(html);
}
}

View File

@@ -133,9 +133,9 @@ public class EmlToPdf {
EmlToPdfRequest request,
byte[] emlBytes,
String fileName,
boolean disableSanitize,
stirling.software.common.service.CustomPDFDocumentFactory pdfDocumentFactory,
TempFileManager tempFileManager)
TempFileManager tempFileManager,
CustomHtmlSanitizer customHtmlSanitizer)
throws IOException, InterruptedException {
validateEmlInput(emlBytes);
@@ -155,7 +155,11 @@ public class EmlToPdf {
// Convert HTML to PDF
byte[] pdfBytes =
convertHtmlToPdf(
weasyprintPath, request, htmlContent, disableSanitize, tempFileManager);
weasyprintPath,
request,
htmlContent,
tempFileManager,
customHtmlSanitizer);
// Attach files if available and requested
if (shouldAttachFiles(emailContent, request)) {
@@ -196,8 +200,8 @@ public class EmlToPdf {
String weasyprintPath,
EmlToPdfRequest request,
String htmlContent,
boolean disableSanitize,
TempFileManager tempFileManager)
TempFileManager tempFileManager,
CustomHtmlSanitizer customHtmlSanitizer)
throws IOException, InterruptedException {
HTMLToPdfRequest htmlRequest = createHtmlRequest(request);
@@ -208,8 +212,8 @@ public class EmlToPdf {
htmlRequest,
htmlContent.getBytes(StandardCharsets.UTF_8),
"email.html",
disableSanitize,
tempFileManager);
tempFileManager,
customHtmlSanitizer);
} catch (IOException | InterruptedException e) {
log.warn("Initial HTML to PDF conversion failed, trying with simplified HTML");
String simplifiedHtml = simplifyHtmlContent(htmlContent);
@@ -218,8 +222,8 @@ public class EmlToPdf {
htmlRequest,
simplifiedHtml.getBytes(StandardCharsets.UTF_8),
"email.html",
disableSanitize,
tempFileManager);
tempFileManager,
customHtmlSanitizer);
}
}

View File

@@ -26,8 +26,8 @@ public class FileToPdf {
HTMLToPdfRequest request,
byte[] fileBytes,
String fileName,
boolean disableSanitize,
TempFileManager tempFileManager)
TempFileManager tempFileManager,
CustomHtmlSanitizer customHtmlSanitizer)
throws IOException, InterruptedException {
try (TempFile tempOutputFile = new TempFile(tempFileManager, ".pdf")) {
@@ -39,14 +39,15 @@ public class FileToPdf {
if (fileName.toLowerCase().endsWith(".html")) {
String sanitizedHtml =
sanitizeHtmlContent(
new String(fileBytes, StandardCharsets.UTF_8), disableSanitize);
new String(fileBytes, StandardCharsets.UTF_8),
customHtmlSanitizer);
Files.write(
tempInputFile.getPath(),
sanitizedHtml.getBytes(StandardCharsets.UTF_8));
} else if (fileName.toLowerCase().endsWith(".zip")) {
Files.write(tempInputFile.getPath(), fileBytes);
sanitizeHtmlFilesInZip(
tempInputFile.getPath(), disableSanitize, tempFileManager);
tempInputFile.getPath(), tempFileManager, customHtmlSanitizer);
} else {
throw ExceptionUtils.createHtmlFileRequiredException();
}
@@ -78,12 +79,15 @@ public class FileToPdf {
} // tempOutputFile auto-closed
}
private static String sanitizeHtmlContent(String htmlContent, boolean disableSanitize) {
return (!disableSanitize) ? CustomHtmlSanitizer.sanitize(htmlContent) : htmlContent;
private static String sanitizeHtmlContent(
String htmlContent, CustomHtmlSanitizer customHtmlSanitizer) {
return customHtmlSanitizer.sanitize(htmlContent);
}
private static void sanitizeHtmlFilesInZip(
Path zipFilePath, boolean disableSanitize, TempFileManager tempFileManager)
Path zipFilePath,
TempFileManager tempFileManager,
CustomHtmlSanitizer customHtmlSanitizer)
throws IOException {
try (TempDirectory tempUnzippedDir = new TempDirectory(tempFileManager)) {
try (ZipInputStream zipIn =
@@ -99,7 +103,8 @@ public class FileToPdf {
|| entry.getName().toLowerCase().endsWith(".htm")) {
String content =
new String(zipIn.readAllBytes(), StandardCharsets.UTF_8);
String sanitizedContent = sanitizeHtmlContent(content, disableSanitize);
String sanitizedContent =
sanitizeHtmlContent(content, customHtmlSanitizer);
Files.write(
filePath, sanitizedContent.getBytes(StandardCharsets.UTF_8));
} else {