Merge pull request #10752 from RasmusWL/pymssql

Python: DB Modeling: Add `pymssql` and `executemany` in general

Author: RasmusWL

docs/codeql/support/reusables/frameworks.rst

@@ -226,6 +226,8 @@ and the CodeQL library pack ``codeql/python-all`` (`changelog <https://github.co
    MySQL-python, Database
    mysqlclient, Database
    psycopg2, Database
+   pymssql, Database
+   PyMySQL, Database
    sqlite3, Database
    Flask-SQLAlchemy, Database ORM
    peewee, Database ORM

python/ql/lib/semmle/python/Frameworks.qll

@@ -37,6 +37,7 @@ private import semmle.python.frameworks.Peewee
 private import semmle.python.frameworks.Psycopg2
 private import semmle.python.frameworks.Pycurl
 private import semmle.python.frameworks.Pydantic
+private import semmle.python.frameworks.Pymssql
 private import semmle.python.frameworks.PyMySQL
 private import semmle.python.frameworks.Requests
 private import semmle.python.frameworks.RestFramework
@@ -51,6 +52,6 @@ private import semmle.python.frameworks.Tornado
 private import semmle.python.frameworks.Twisted
 private import semmle.python.frameworks.Ujson
 private import semmle.python.frameworks.Urllib3
+private import semmle.python.frameworks.Xmltodict
 private import semmle.python.frameworks.Yaml
 private import semmle.python.frameworks.Yarl
-private import semmle.python.frameworks.Xmltodict

python/ql/lib/semmle/python/frameworks/Mysql.qll

@@ -21,17 +21,11 @@ private import semmle.python.frameworks.PEP249
  * - https://dev.mysql.com/doc/connector-python/en/connector-python-example-connecting.html
  */
 private module Mysql {
-  // ---------------------------------------------------------------------------
-  // mysql
-  // ---------------------------------------------------------------------------
-  /** Provides models for the `mysql` module. */
-  module MysqlMod {
-    /**
-     * The mysql.connector module
-     * See https://dev.mysql.com/doc/connector-python/en/connector-python-example-connecting.html
-     */
-    class MysqlConnector extends PEP249::PEP249ModuleApiNode {
-      MysqlConnector() { this = API::moduleImport("mysql").getMember("connector") }
-    }
+  /**
+   * The mysql.connector module
+   * See https://dev.mysql.com/doc/connector-python/en/connector-python-example-connecting.html
+   */
+  class MysqlConnector extends PEP249::PEP249ModuleApiNode {
+    MysqlConnector() { this = API::moduleImport("mysql").getMember("connector") }
   }
 }

python/ql/lib/semmle/python/frameworks/Pymssql.qll

@@ -0,0 +1,25 @@
+/**
+ * Provides classes modeling security-relevant aspects of the `pymssql` PyPI package.
+ * See https://pypi.org/project/pymssql/
+ */
+
+private import python
+private import semmle.python.dataflow.new.DataFlow
+private import semmle.python.dataflow.new.RemoteFlowSources
+private import semmle.python.Concepts
+private import semmle.python.ApiGraphs
+private import semmle.python.frameworks.PEP249
+
+/**
+ * Provides models for the `pymssql` PyPI package.
+ * See https://pypi.org/project/pymssql/
+ */
+private module Pymssql {
+  /**
+   * A model of `pymssql` as a module that implements PEP 249, providing ways to execute SQL statements
+   * against a database.
+   */
+  class PymssqlPEP249 extends PEP249::PEP249ModuleApiNode {
+    PymssqlPEP249() { this = API::moduleImport("pymssql") }
+  }
+}

python/ql/lib/semmle/python/frameworks/internal/PEP249Impl.qll

@@ -146,7 +146,7 @@ module PEP249 {
    * Note: while `execute` method on a connection is not part of PEP249, if it is used, we
    * recognize it as an alias for constructing a cursor and calling `execute` on it.
    *
-   * See https://www.python.org/dev/peps/pep-0249/#id15.
+   * See https://peps.python.org/pep-0249/#execute.
    */
   private DataFlow::TypeTrackingNode execute(DataFlow::TypeTracker t) {
     t.startInAttr("execute") and
@@ -161,14 +161,44 @@ module PEP249 {
    * Note: while `execute` method on a connection is not part of PEP249, if it is used, we
    * recognize it as an alias for constructing a cursor and calling `execute` on it.
    *
-   * See https://www.python.org/dev/peps/pep-0249/#id15.
+   * See https://peps.python.org/pep-0249/#execute.
    */
   DataFlow::Node execute() { execute(DataFlow::TypeTracker::end()).flowsTo(result) }
 
-  /** A call to the `execute` method on a cursor (or on a connection). */
+  /**
+   * A call to the `execute` method on a cursor or a connection.
+   *
+   * See https://peps.python.org/pep-0249/#execute
+   *
+   * Note: While `execute` method on a connection is not part of PEP249, if it is used, we
+   * recognize it as an alias for constructing a cursor and calling `execute` on it.
+   */
   private class ExecuteCall extends SqlExecution::Range, DataFlow::CallCfgNode {
     ExecuteCall() { this.getFunction() = execute() }
 
     override DataFlow::Node getSql() { result in [this.getArg(0), this.getArgByName("sql")] }
   }
+
+  private DataFlow::TypeTrackingNode executemany(DataFlow::TypeTracker t) {
+    t.startInAttr("executemany") and
+    result in [Cursor::instance(), Connection::instance()]
+    or
+    exists(DataFlow::TypeTracker t2 | result = executemany(t2).track(t2, t))
+  }
+
+  private DataFlow::Node executemany() { executemany(DataFlow::TypeTracker::end()).flowsTo(result) }
+
+  /**
+   * A call to the `executemany` method on a cursor or a connection.
+   *
+   * See https://peps.python.org/pep-0249/#executemany
+   *
+   * Note: While `executemany` method on a connection is not part of PEP249, if it is used, we
+   * recognize it as an alias for constructing a cursor and calling `executemany` on it.
+   */
+  private class ExecutemanyCall extends SqlExecution::Range, DataFlow::CallCfgNode {
+    ExecutemanyCall() { this.getFunction() = executemany() }
+
+    override DataFlow::Node getSql() { result in [this.getArg(0), this.getArgByName("sql")] }
+  }
 }

python/ql/src/change-notes/2022-10-10-pep249-executemany-modeling.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* Added model of `executemany` calls on PEP-249 compliant database APIs, resulting in additional sinks for `py/sql-injection`.

python/ql/src/change-notes/2022-10-10-pymssql-modeling.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* Added model of `pymssql` PyPI package as a SQL interface following PEP249, resulting in additional sinks for `py/sql-injection`.

python/ql/test/library-tests/frameworks/pymssql/ConceptsTest.expected

@@ -0,0 +1,2 @@
+import python
+import experimental.meta.ConceptsTest

python/ql/test/library-tests/frameworks/pymssql/ConceptsTest.ql

@@ -0,0 +1,6 @@
+import pymssql
+connection = pymssql.connect(host="localhost", user="user", password="passwd")
+
+cursor = connection.cursor()
+cursor.execute("some sql", (42,))  # $ getSql="some sql"
+cursor.executemany("some sql", [(42,)])  # $ getSql="some sql"