Python : Improve Xpath Injection Query

python/ql/src/experimental/Security/CWE-643-new/Xpath.ql

@@ -0,0 +1,36 @@
+/**
+ * @name XPath query built from user-controlled sources
+ * @description Building a XPath query from user-controlled sources is vulnerable to insertion of
+ *              malicious Xpath code by the user.
+ * @kind path-problem
+ * @problem.severity error
+ * @precision high
+ * @id py/xpath-injection-new
+ * @tags security
+ *       external/cwe/cwe-643
+ */
+
+private import python
+private import semmle.python.Concepts
+private import semmle.python.dataflow.new.TaintTracking
+private import semmle.python.Concepts
+private import semmle.python.ApiGraphs
+private import semmle.python.dataflow.new.RemoteFlowSources
+private import semmle.python.dataflow.new.BarrierGuards
+import XpathInjection::XpathInjection
+
+class XpathInjectionConfiguration extends TaintTracking::Configuration {
+  XpathInjectionConfiguration() { this = "PathNotNormalizedConfiguration" }
+
+  override predicate isSource(DataFlow::Node source) { source instanceof Source }
+
+  override predicate isSink(DataFlow::Node sink) { sink instanceof Sink }
+  // override predicate isAdditionalTaintStep(DataFlow::Node node1, DataFlow::Node node2) {
+  //   exists(AdditionalFlowStep af | af.isAdditionalTaintStep(node1, node2))
+  // }
+}
+
+from XpathInjectionConfiguration config, DataFlow::PathNode source, DataFlow::PathNode sink
+where config.hasFlowPath(source, sink)
+select sink, source, sink, "This Xpath query depends on $@.", source,
+  "a user-provided value"

python/ql/src/experimental/Security/CWE-643-new/XpathInjection.qll

@@ -0,0 +1,35 @@
+/**
+ * Provides a taint-tracking configuration for detecting "Xpath Injection" vulnerabilities.
+ *
+ * Note, for performance reasons: only import this file if
+ * `XpathInjection::Configuration` is needed, otherwise
+ * `XpathInjectionCustomizations` should be imported instead.
+ */
+
+private import python
+import semmle.python.dataflow.new.DataFlow
+import semmle.python.dataflow.new.TaintTracking
+
+/**
+ * Provides a taint-tracking configuration for detecting "Xpath Injection" vulnerabilities.
+ */
+module XpathInjection {
+  import XpathInjectionCustomizations::XpathInjection
+
+  /**
+   * A taint-tracking configuration for detecting "Xpath Injection" vulnerabilities.
+   */
+  class Configuration extends TaintTracking::Configuration {
+    Configuration() { this = "Xpath Injection" }
+
+    override predicate isSource(DataFlow::Node source) { source instanceof Source }
+
+    override predicate isSink(DataFlow::Node sink) { sink instanceof Sink }
+
+    override predicate isSanitizer(DataFlow::Node node) { node instanceof Sanitizer }
+
+    override predicate isSanitizerGuard(DataFlow::BarrierGuard guard) {
+      guard instanceof SanitizerGuard
+    }
+  }
+}

python/ql/src/experimental/Security/CWE-643-new/XpathInjectionCustomizations.qll

@@ -0,0 +1,105 @@
+/**
+ * Provides class and predicates to track external data that
+ * may represent malicious xpath query objects.
+ *
+ * This module is intended to be imported into a taint-tracking query.
+ */
+
+private import python
+private import semmle.python.Concepts
+private import semmle.python.dataflow.new.TaintTracking
+private import semmle.python.Concepts
+private import semmle.python.ApiGraphs
+private import semmle.python.dataflow.new.RemoteFlowSources
+private import semmle.python.dataflow.new.BarrierGuards
+
+/** Models Xpath Injection related classes and functions */
+module XpathInjection {
+  /**
+   * A data flow source for "XPath injection" vulnerabilities.
+   */
+  abstract class Source extends DataFlow::Node { }
+
+  /**
+   * A data flow sink for "XPath injection" vulnerabilities.
+   */
+  abstract class Sink extends DataFlow::Node { }
+
+  /**
+   * A sanitizer for "XPath injection" vulnerabilities.
+   */
+  abstract class Sanitizer extends DataFlow::Node { }
+
+  /**
+   * A sanitizer guard for "XPath injection" vulnerabilities.
+   */
+  abstract class SanitizerGuard extends DataFlow::BarrierGuard { }
+
+  /**
+   * A source of remote user input, considered as a flow source.
+   */
+  class RemoteFlowSourceAsSource extends Source, RemoteFlowSource { }
+
+  /** Returns an API node referring to `lxml.etree` */
+  API::Node etree() { result = API::moduleImport("lxml").getMember("etree") }
+
+  /** Returns an API node referring to `lxml.etree` */
+  API::Node etreeFromString() { result = etree().getMember("fromstring") }
+
+  /** Returns an API node referring to `lxml.etree.parse` */
+  API::Node etreeParse() { result = etree().getMember("parse") }
+
+  /** Returns an API node referring to `lxml.etree.parse` */
+  API::Node libxml2parseFile() { result = API::moduleImport("libxml2").getMember("parseFile") }
+
+  /**
+   * A Sink representing an argument to `etree.XPath` or `etree.ETXpath` call.
+   *
+   *    from lxml import etree
+   *    root = etree.XML("<xmlContent>")
+   *    find_text = etree.XPath("`sink`")
+   *    find_text = etree.ETXpath("`sink`")
+   */
+  private class EtreeXpathArgument extends Sink {
+    EtreeXpathArgument() { this = etree().getMember(["XPath", "ETXpath"]).getACall().getArg(0) }
+  }
+
+  /**
+   * A Sink representing an argument to the `etree.XPath` call.
+   *
+   *    from lxml import etree
+   *    root =  etree.fromstring(file(XML_DB).read(), XMLParser())
+   *    find_text = root.xpath("`sink`")
+   */
+  private class EtreeFromstringXpathArgument extends Sink {
+    EtreeFromstringXpathArgument() {
+      this = etreeFromString().getReturn().getMember("xpath").getACall().getArg(0)
+    }
+  }
+
+  /**
+   * A Sink representing an argument to the `xpath` call to a parsed xml document.
+   *
+   *    from lxml import etree
+   *    from io import StringIO
+   *    f = StringIO('<foo><bar></bar></foo>')
+   *    tree = etree.parse(f)
+   *    r = tree.xpath('`sink`')
+   */
+  private class ParseXpathArgument extends Sink {
+    ParseXpathArgument() { this = etreeParse().getReturn().getMember("xpath").getACall().getArg(0) }
+  }
+
+  /**
+   * A Sink representing an argument to the `xpathEval` call to a parsed libxml2 document.
+   *
+   *    import libxml2
+   *    tree = libxml2.parseFile("file.xml")
+   *    r = tree.xpathEval('`sink`')
+   */
+  private class ParseFileXpathEvalArgument extends Sink {
+    ParseFileXpathEvalArgument() {
+      this = libxml2parseFile().getReturn().getMember("xpathEval").getACall().getArg(0)
+    }
+  }
+}