C++: Add ExternalAPI library files (for AST and IR).

cpp/ql/src/semmle/code/cpp/security/ExternalAPIs.qll

@@ -0,0 +1,50 @@
+/**
+ * Definitions for reasoning about untrusted data used in APIs defined outside the
+ * database.
+ */
+
+private import cpp
+private import semmle.code.cpp.models.interfaces.DataFlow
+private import semmle.code.cpp.models.interfaces.Taint
+import implementation.ExternalAPIsSpecific
+
+/** A node representing untrusted data being passed to an external API. */
+class UntrustedExternalAPIDataNode extends ExternalAPIDataNode {
+  UntrustedExternalAPIDataNode() { any(UntrustedDataToExternalAPIConfig c).hasFlow(_, this) }
+
+  /** Gets a source of untrusted data which is passed to this external API data node. */
+  DataFlow::Node getAnUntrustedSource() {
+    any(UntrustedDataToExternalAPIConfig c).hasFlow(result, this)
+  }
+}
+
+private newtype TExternalAPI =
+  TExternalAPIParameter(Function f, int index) {
+    exists(UntrustedExternalAPIDataNode n |
+      f = n.getExternalFunction() and
+      index = n.getIndex()
+    )
+  }
+
+/** An external API which is used with untrusted data. */
+class ExternalAPIUsedWithUntrustedData extends TExternalAPI {
+  /** Gets a possibly untrusted use of this external API. */
+  UntrustedExternalAPIDataNode getUntrustedDataNode() {
+    this = TExternalAPIParameter(result.getExternalFunction(), result.getIndex())
+  }
+
+  /** Gets the number of untrusted sources used with this external API. */
+  int getNumberOfUntrustedSources() {
+    result = count(getUntrustedDataNode().getAnUntrustedSource())
+  }
+
+  /** Gets a textual representation of this element. */
+  string toString() {
+    exists(Function f, int index, string indexString |
+      if index = -1 then indexString = "qualifier" else indexString = "param " + index
+    |
+      this = TExternalAPIParameter(f, index) and
+      result = f.toString() + " [" + indexString + "]"
+    )
+  }
+}

cpp/ql/src/semmle/code/cpp/security/implementation/ExternalAPIsSpecific.qll

@@ -0,0 +1,52 @@
+import semmle.code.cpp.dataflow.TaintTracking
+import semmle.code.cpp.models.interfaces.FlowSource
+import semmle.code.cpp.models.interfaces.DataFlow
+import SafeExternalAPIFunction
+
+/** A node representing untrusted data being passed to an external API. */
+class ExternalAPIDataNode extends DataFlow::Node {
+  Call call;
+  int i;
+
+  ExternalAPIDataNode() {
+    // Argument to call to a function
+    (
+      this.asExpr() = call.getArgument(i)
+      or
+      i = -1 and this.asExpr() = call.getQualifier()
+    ) and
+    exists(Function f |
+      f = call.getTarget() and
+      // Defined outside the source archive
+      not f.hasDefinition() and
+      // Not already modeled as a dataflow or taint step
+      not f instanceof DataFlowFunction and
+      not f instanceof TaintFunction and
+      // Not a call to a known safe external API
+      not f instanceof SafeExternalAPIFunction
+    )
+  }
+
+  /** Gets the called API `Function`. */
+  Function getExternalFunction() { result = call.getTarget() }
+
+  /** Gets the index which is passed untrusted data (where -1 indicates the qualifier). */
+  int getIndex() { result = i }
+
+  /** Gets the description of the function being called. */
+  string getFunctionDescription() { result = getExternalFunction().toString() }
+}
+
+/** A configuration for tracking flow from `RemoteFlowSource`s to `ExternalAPIDataNode`s. */
+class UntrustedDataToExternalAPIConfig extends TaintTracking::Configuration {
+  UntrustedDataToExternalAPIConfig() { this = "UntrustedDataToExternalAPIConfig" }
+
+  override predicate isSource(DataFlow::Node source) {
+    exists(RemoteFlowFunction remoteFlow |
+      remoteFlow = source.asExpr().(Call).getTarget() and
+      remoteFlow.hasRemoteFlowSource(_, _)
+    )
+  }
+
+  override predicate isSink(DataFlow::Node sink) { sink instanceof ExternalAPIDataNode }
+}

cpp/ql/src/semmle/code/cpp/security/implementation/SafeExternalAPIFunction.qll

@@ -0,0 +1,11 @@
+private import cpp
+
+/**
+ * A `Function` that is considered a "safe" external API from a security perspective.
+ */
+abstract class SafeExternalAPIFunction extends Function { }
+
+/** The default set of "safe" external APIs. */
+private class DefaultSafeExternalAPIFunction extends SafeExternalAPIFunction {
+  DefaultSafeExternalAPIFunction() { this.hasGlobalName(["strcmp", "strlen", "memcmp"]) }
+}

cpp/ql/src/semmle/code/cpp/security/ir/ExternalAPIs.qll

@@ -0,0 +1,50 @@
+/**
+ * Definitions for reasoning about untrusted data used in APIs defined outside the
+ * database.
+ */
+
+private import cpp
+private import semmle.code.cpp.models.interfaces.DataFlow
+private import semmle.code.cpp.models.interfaces.Taint
+import implementation.ExternalAPIsSpecific
+
+/** A node representing untrusted data being passed to an external API. */
+class UntrustedExternalAPIDataNode extends ExternalAPIDataNode {
+  UntrustedExternalAPIDataNode() { any(UntrustedDataToExternalAPIConfig c).hasFlow(_, this) }
+
+  /** Gets a source of untrusted data which is passed to this external API data node. */
+  DataFlow::Node getAnUntrustedSource() {
+    any(UntrustedDataToExternalAPIConfig c).hasFlow(result, this)
+  }
+}
+
+private newtype TExternalAPI =
+  TExternalAPIParameter(Function f, int index) {
+    exists(UntrustedExternalAPIDataNode n |
+      f = n.getExternalFunction() and
+      index = n.getIndex()
+    )
+  }
+
+/** An external API which is used with untrusted data. */
+class ExternalAPIUsedWithUntrustedData extends TExternalAPI {
+  /** Gets a possibly untrusted use of this external API. */
+  UntrustedExternalAPIDataNode getUntrustedDataNode() {
+    this = TExternalAPIParameter(result.getExternalFunction(), result.getIndex())
+  }
+
+  /** Gets the number of untrusted sources used with this external API. */
+  int getNumberOfUntrustedSources() {
+    result = count(getUntrustedDataNode().getAnUntrustedSource())
+  }
+
+  /** Gets a textual representation of this element. */
+  string toString() {
+    exists(Function f, int index, string indexString |
+      if index = -1 then indexString = "qualifier" else indexString = "param " + index
+    |
+      this = TExternalAPIParameter(f, index) and
+      result = f.toString() + " [" + indexString + "]"
+    )
+  }
+}

cpp/ql/src/semmle/code/cpp/security/ir/implementation/ExternalAPIsSpecific.qll

@@ -0,0 +1,47 @@
+import semmle.code.cpp.ir.dataflow.TaintTracking
+private import semmle.code.cpp.security.FlowSources
+private import semmle.code.cpp.models.interfaces.DataFlow
+import SafeExternalAPIFunction
+
+/** A node representing untrusted data being passed to an external API. */
+class ExternalAPIDataNode extends DataFlow::Node {
+  Call call;
+  int i;
+
+  ExternalAPIDataNode() {
+    // Argument to call to a function
+    (
+      this.asExpr() = call.getArgument(i)
+      or
+      i = -1 and this.asExpr() = call.getQualifier()
+    ) and
+    exists(Function f |
+      f = call.getTarget() and
+      // Defined outside the source archive
+      not f.hasDefinition() and
+      // Not already modeled as a dataflow or taint step
+      not f instanceof DataFlowFunction and
+      not f instanceof TaintFunction and
+      // Not a call to a known safe external API
+      not f instanceof SafeExternalAPIFunction
+    )
+  }
+
+  /** Gets the called API `Function`. */
+  Function getExternalFunction() { result = call.getTarget() }
+
+  /** Gets the index which is passed untrusted data (where -1 indicates the qualifier). */
+  int getIndex() { result = i }
+
+  /** Gets the description of the function being called. */
+  string getFunctionDescription() { result = getExternalFunction().toString() }
+}
+
+/** A configuration for tracking flow from `RemoteFlowSource`s to `ExternalAPIDataNode`s. */
+class UntrustedDataToExternalAPIConfig extends TaintTracking::Configuration {
+  UntrustedDataToExternalAPIConfig() { this = "UntrustedDataToExternalAPIConfigIR" }
+
+  override predicate isSource(DataFlow::Node source) { source instanceof RemoteFlowSource }
+
+  override predicate isSink(DataFlow::Node sink) { sink instanceof ExternalAPIDataNode }
+}

cpp/ql/src/semmle/code/cpp/security/ir/implementation/SafeExternalAPIFunction.qll

@@ -0,0 +1,11 @@
+private import cpp
+
+/**
+ * A `Function` that is considered a "safe" external API from a security perspective.
+ */
+abstract class SafeExternalAPIFunction extends Function { }
+
+/** The default set of "safe" external APIs. */
+private class DefaultSafeExternalAPIFunction extends SafeExternalAPIFunction {
+  DefaultSafeExternalAPIFunction() { this.hasGlobalName(["strcmp", "strlen", "memcmp"]) }
+}