Python: Port py/code-injection to use proper source/sink customization

python/ql/src/Security/CWE-094/CodeInjection.ql

@@ -19,7 +19,7 @@ import python
 import semmle.python.security.dataflow.CodeInjection
 import DataFlow::PathGraph
 
-from CodeInjectionConfiguration config, DataFlow::PathNode source, DataFlow::PathNode sink
+from CodeInjection::Configuration config, DataFlow::PathNode source, DataFlow::PathNode sink
 where config.hasFlowPath(source, sink)
 select sink.getNode(), source, sink, "$@ flows to here and is interpreted as code.",
   source.getNode(), "A user-provided value"

python/ql/src/semmle/python/security/dataflow/CodeInjection.qll

@@ -1,26 +1,42 @@
 /**
- * Provides a taint-tracking configuration for detecting code injection
- * vulnerabilities.
+ * Provides a taint-tracking configuration for detecting "code injection" vulnerabilities.
+ *
+ * Note, for performance reasons: only import this file if
+ * `CodeInjection::Configuration` is needed, otherwise
+ * `CodeInjectionCustomizations` should be imported instead.
  */
 
-import python
+private import python
 import semmle.python.dataflow.new.DataFlow
 import semmle.python.dataflow.new.TaintTracking
-import semmle.python.Concepts
-import semmle.python.dataflow.new.RemoteFlowSources
-import semmle.python.dataflow.new.BarrierGuards
 
 /**
- * A taint-tracking configuration for detecting code injection vulnerabilities.
+ * Provides a taint-tracking configuration for detecting "code injection" vulnerabilities.
  */
-class CodeInjectionConfiguration extends TaintTracking::Configuration {
-  CodeInjectionConfiguration() { this = "CodeInjectionConfiguration" }
+module CodeInjection {
+  import CodeInjectionCustomizations::CodeInjection
 
-  override predicate isSource(DataFlow::Node source) { source instanceof RemoteFlowSource }
+  /**
+   * A taint-tracking configuration for detecting "code injection" vulnerabilities.
+   */
+  class Configuration extends TaintTracking::Configuration {
+    Configuration() { this = "CodeInjection" }
 
-  override predicate isSink(DataFlow::Node sink) { sink = any(CodeExecution e).getCode() }
+    override predicate isSource(DataFlow::Node source) { source instanceof Source }
 
-  override predicate isSanitizerGuard(DataFlow::BarrierGuard guard) {
-    guard instanceof StringConstCompare
+    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
+    }
   }
 }
+
+/**
+ * DEPRECATED: Don't extend this class for customization, since this will lead to bad
+ * performance, instead use the new `CodeInjectionCustomizations.qll` file, and extend
+ * its' classes.
+ */
+deprecated class CodeInjectionConfiguration = CodeInjection::Configuration;

python/ql/src/semmle/python/security/dataflow/CodeInjectionCustomizations.qll

@@ -0,0 +1,55 @@
+/**
+ * Provides default sources, sinks and sanitizers for detecting
+ * "code injection"
+ * vulnerabilities, as well as extension points for adding your own.
+ */
+
+private import python
+private import semmle.python.dataflow.new.DataFlow
+private import semmle.python.Concepts
+private import semmle.python.dataflow.new.RemoteFlowSources
+private import semmle.python.dataflow.new.BarrierGuards
+
+/**
+ * Provides default sources, sinks and sanitizers for detecting
+ * "code injection"
+ * vulnerabilities, as well as extension points for adding your own.
+ */
+module CodeInjection {
+  /**
+   * A data flow source for "code injection" vulnerabilities.
+   */
+  abstract class Source extends DataFlow::Node { }
+
+  /**
+   * A data flow sink for "code injection" vulnerabilities.
+   */
+  abstract class Sink extends DataFlow::Node { }
+
+  /**
+   * A sanitizer for "code injection" vulnerabilities.
+   */
+  abstract class Sanitizer extends DataFlow::Node { }
+
+  /**
+   * A sanitizer guard for "code injection" vulnerabilities.
+   */
+  abstract class SanitizerGuard extends DataFlow::BarrierGuard { }
+
+  /**
+   * A source of remote user input, considered as a flow source.
+   */
+  class RemoteFlowSourceAsSource extends Source, RemoteFlowSource { }
+
+  /**
+   * A code execution, considered as a flow sink.
+   */
+  class CodeExecutionAsSink extends Sink {
+    CodeExecutionAsSink() { this = any(CodeExecution e).getCode() }
+  }
+
+  /**
+   * A comparison with a constant string, considered as a sanitizer-guard.
+   */
+  class StringConstCompareAsSanitizerGuard extends SanitizerGuard, StringConstCompare { }
+}