From 228dd2952a9c3a0a2652a2c100ca023268628272 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?V=C3=ADctor=20Fern=C3=A1ndez=20Poyatos?=
 <victor@prowler.com>
Date: Tue, 1 Apr 2025 11:55:14 +0200
Subject: [PATCH] fix(scans): Handle duplicated scan tasks (#7401)

---
 api/CHANGELOG.md               |  7 ++++++
 api/src/backend/tasks/tasks.py | 45 +++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/api/CHANGELOG.md b/api/CHANGELOG.md
index 09cc4369ae..db0d696488 100644
--- a/api/CHANGELOG.md
+++ b/api/CHANGELOG.md
@@ -15,6 +15,13 @@ All notable changes to the **Prowler API** are documented in this file.
 
 ---
 
+## [v1.5.3] (Prowler v5.4.3)
+
+### Fixed
+- Added duplicated scheduled scans handling ([#7401])(https://github.com/prowler-cloud/prowler/pull/7401).
+
+---
+
 ## [v1.5.2] (Prowler v5.4.2)
 
 ### Changed
diff --git a/api/src/backend/tasks/tasks.py b/api/src/backend/tasks/tasks.py
index c9b8d1ab2a..12e7c7cf01 100644
--- a/api/src/backend/tasks/tasks.py
+++ b/api/src/backend/tasks/tasks.py
@@ -1,3 +1,4 @@
+from datetime import datetime, timedelta, timezone
 from pathlib import Path
 from shutil import rmtree
 
@@ -21,6 +22,7 @@ from api.db_utils import rls_transaction
 from api.decorators import set_tenant
 from api.models import Finding, Provider, Scan, ScanSummary, StateChoices
 from api.utils import initialize_prowler_provider
+from api.v1.serializers import ScanTaskSerializer
 from prowler.lib.outputs.finding import Finding as FindingOutput
 
 logger = get_task_logger(__name__)
@@ -128,6 +130,43 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
         periodic_task_instance = PeriodicTask.objects.get(
             name=f"scan-perform-scheduled-{provider_id}"
         )
+
+        executed_scan = Scan.objects.filter(
+            tenant_id=tenant_id,
+            provider_id=provider_id,
+            task__task_runner_task__task_id=task_id,
+        ).order_by("completed_at")
+
+        if (
+            Scan.objects.filter(
+                tenant_id=tenant_id,
+                provider_id=provider_id,
+                trigger=Scan.TriggerChoices.SCHEDULED,
+                state=StateChoices.EXECUTING,
+                scheduler_task_id=periodic_task_instance.id,
+                scheduled_at__date=datetime.now(timezone.utc).date(),
+            ).exists()
+            or executed_scan.exists()
+        ):
+            # Duplicated task execution due to visibility timeout or scan is already running
+            logger.warning(f"Duplicated scheduled scan for provider {provider_id}.")
+            try:
+                affected_scan = executed_scan.first()
+                if not affected_scan:
+                    raise ValueError(
+                        "Error retrieving affected scan details after detecting duplicated scheduled "
+                        "scan."
+                    )
+                # Return the affected scan details to avoid losing data
+                serializer = ScanTaskSerializer(instance=affected_scan)
+            except Exception as duplicated_scan_exception:
+                logger.error(
+                    f"Duplicated scheduled scan for provider {provider_id}. Error retrieving affected scan details: "
+                    f"{str(duplicated_scan_exception)}"
+                )
+                raise duplicated_scan_exception
+            return serializer.data
+
         next_scan_datetime = get_next_execution_datetime(task_id, provider_id)
         scan_instance, _ = Scan.objects.get_or_create(
             tenant_id=tenant_id,
@@ -135,7 +174,11 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
             trigger=Scan.TriggerChoices.SCHEDULED,
             state__in=(StateChoices.SCHEDULED, StateChoices.AVAILABLE),
             scheduler_task_id=periodic_task_instance.id,
-            defaults={"state": StateChoices.SCHEDULED},
+            defaults={
+                "state": StateChoices.SCHEDULED,
+                "name": "Daily scheduled scan",
+                "scheduled_at": next_scan_datetime - timedelta(days=1),
+            },
         )
 
         scan_instance.task_id = task_id