8000 Fillup missing vulnerabilities summary by TG1999 · Pull Request #1767 · aboutcode-org/vulnerablecode · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Fillup missing vulnerabilities summary #1767

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Apr 1, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions vulnerabilities/improvers/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
from vulnerabilities.pipelines import enhance_with_kev
from vulnerabilities.pipelines import enhance_with_metasploit
from vulnerabilities.pipelines import flag_ghost_packages
from vulnerabilities.pipelines import populate_vulnerability_summary_pipeline
from vulnerabilities.pipelines import remove_duplicate_advisories

IMPROVERS_REGISTRY = [
Expand Down Expand Up @@ -47,6 +48,7 @@
collect_commits.CollectFixCommitsPipeline,
add_cvss31_to_CVEs.CVEAdvisoryMappingPipeline,
remove_duplicate_advisories.RemoveDuplicateAdvisoriesPipeline,
populate_vulnerability_summary_pipeline.PopulateVulnerabilitySummariesPipeline,
]

IMPROVERS_REGISTRY = {
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
#
# Copyright (c) nexB Inc. and others. All rights reserved.
# VulnerableCode is a trademark of nexB Inc.
# SPDX-License-Identifier: Apache-2.0
# See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
# See https://github.com/aboutcode-org/vulnerablecode for support or download.
# See https://aboutcode.org for more information about nexB OSS projects.
#

import logging

from aboutcode.pipeline import LoopProgress
from django.db.models import Q

from vulnerabilities.models import Advisory
from vulnerabilities.models import Vulnerability
from vulnerabilities.pipelines import VulnerableCodePipeline


class PopulateVulnerabilitySummariesPipeline(VulnerableCodePipeline):
"""Pipeline to populate missing vulnerability summaries from advisories."""

pipeline_id = "populate_vulnerability_summaries"

@classmethod
def steps(cls):
return (cls.populate_missing_summaries,)

def populate_missing_summaries(self):
"""Find vulnerabilities with missing summaries and populate them using advisories with the same aliases."""
vulnerabilities_qs = Vulnerability.objects.filter(summary="")
self.log(
f"Processing {vulnerabilities_qs.count()} vulnerabilities without summaries",
level=logging.INFO,
)

progress = LoopProgress(total_iterations=vulnerabilities_qs.count(), logger=self.log)

vulnerabilities_to_be_updated = []

for vulnerability in progress.iter(vulnerabilities_qs.iterator()):
cve_alias = vulnerability.aliases.filter(alias__startswith="CVE-").first()

if not cve_alias:
self.log(
f"Vulnerability {vulnerability.vulnerability_id} has no CVE alias",
level=logging.DEBUG,
)
continue

matching_advisories = Advisory.objects.filter(
aliases=cve_alias, created_by="nvd_importer"
).exclude(summary="")

if matching_advisories.exists():
best_advisory = matching_advisories.order_by("-date_collected").first()
# Note: we filtered above to only get non-empty summaries
vulnerability.summary = best_advisory.summary
vulnerabilities_to_be_updated.append(vulnerability)
self.log(
f"Updated summary for vulnerability {vulnerability.vulnerability_id}",
level=logging.INFO,
)
else:
self.log(f"No advisory found for alias {cve_alias}", level=logging.DEBUG)
Vulnerability.objects.bulk_update(vulnerabilities_to_be_updated, ["summary"])
self.log(
f"Successfully populated {len(vulnerabilities_to_be_updated)} vulnerabilities with summary",
level=logging.INFO,
)
self.log("Pipeline completed", level=logging.INFO)
Original file line number Diff line number Diff line change
@@ -0,0 +1,160 @@
#
# Copyright (c) nexB Inc. and others. All rights reserved.
# VulnerableCode is a trademark of nexB Inc.
# SPDX-License-Identifier: Apache-2.0
# See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
# See https://github.com/aboutcode-org/vulnerablecode for support or download.
# See https://aboutcode.org for more information about nexB OSS projects.
#

import datetime
from pathlib import Path

import pytz
from django.test import TestCase

from vulnerabilities.models import Advisory
from vulnerabilities.models import Alias
from vulnerabilities.models import Vulnerability
from vulnerabilities.pipelines.populate_vulnerability_summary_pipeline import (
PopulateVulnerabilitySummariesPipeline,
)


class PopulateVulnerabilitySummariesPipelineTest(TestCase):
def setUp(self):
self.data = Path(__file__).parent.parent / "test_data"

def test_populate_missing_summaries_from_nvd(self):
"""
Test that vulnerabilities without summaries get them from NVD advisories.
"""

# Create a vulnerability without a summary
vulnerability = Vulnerability.objects.create(
vulnerability_id="VCID-1234",
summary="",
)
alias = Alias.objects.create(alias="CVE-2024-1234", vulnerability=vulnerability)

# Create an NVD advisory with a summary
adv = Advisory.objects.create(
summary="Test vulnerability summary",
created_by="nvd_importer",
date_collected=datetime.datetime(2024, 1, 1, tzinfo=pytz.UTC),
unique_content_id="Test",
)
10000 adv.aliases.add(alias)

# Run the pipeline
pipeline = PopulateVulnerabilitySummariesPipeline()
pipeline.populate_missing_summaries()

# Check that the vulnerability now has a summary
vulnerability.refresh_from_db()
self.assertEqual(vulnerability.summary, "Test vulnerability summary")

def test_no_matching_advisory(self):
"""
Test handling of vulnerabilities that have no matching NVD advisory.
"""
# Create a vulnerability without a summary
vulnerability = Vulnerability.objects.create(
vulnerability_id="VCID-1234",
summary="",
)
Alias.objects.create(alias="CVE-2024-1234", vulnerability=vulnerability)

# Run the pipeline
pipeline = PopulateVulnerabilitySummariesPipeline()
pipeline.populate_missing_summaries()

# Check that the vulnerability still has no summary
vulnerability.refresh_from_db()
self.assertEqual(vulnerability.summary, "")

def test_vulnerability_without_alias(self):
"""
Test handling of vulnerabilities that have no aliases.
"""

# Create a vulnerability without a summary or alias
vulnerability = Vulnerability.objects.create(
vulnerability_id="VCID-1234",
summary="",
)

# Run the pipeline
pipeline = PopulateVulnerabilitySummariesPipeline()
pipeline.populate_missing_summaries()

# Check that the vulnerability still has no summary
vulnerability.refresh_from_db()
self.assertEqual(vulnerability.summary, "")

def test_non_nvd_advisory_ignored(self):
"""
Test that advisories from sources other than NVD are ignored.
"""

# Create a vulnerability without a summary
vulnerability = Vulnerability.objects.create(
vulnerability_id="VCID-1234",
summary="",
)
alias = Alias.objects.create(alias="CVE-2024-1234", vulnerability=vulnerability)

# Create a non-NVD advisory with a summary
adv = Advisory.objects.create(
summary="Test vulnerability summary",
created_by="other_importer",
date_collected=datetime.datetime(2024, 1, 1, tzinfo=pytz.UTC),
unique_content_id="Test",
)

adv.aliases.add(alias)

# Run the pipeline
pipeline = PopulateVulnerabilitySummariesPipeline()
pipeline.populate_missing_summaries()

# Check that the vulnerability still has no summary
vulnerability.refresh_from_db()
self.assertEqual(vulnerability.summary, "")

def test_multiple_matching_advisories(self):
"""
Test that the most recent matching advisory is used when there are multiple.
"""
vulnerability = Vulnerability.objects.create(
vulnerability_id="VCID-1234",
summary="",
)
alias = Alias.objects.create(alias="CVE-2024-1234", vulnerability=vulnerability)

# Create two NVD advisories with the same alias
adv1 = Advisory.objects.create(
summary="First matching advisory",
created_by="nvd_importer",
date_collected=datetime.datetime(2024, 1, 1, tzinfo=pytz.UTC),
unique_content_id="Test",
)

adv1.aliases.add(alias)

adv2 = Advisory.objects.create(
summary="Second matching advisory",
created_by="nvd_importer",
date_collected=datetime.datetime(2024, 1, 2, tzinfo=pytz.UTC),
unique_content_id="Test-1",
)

adv2.aliases.add(alias)

# Run the pipeline
pipeline = PopulateVulnerabilitySummariesPipeline()
pipeline.populate_missing_summaries()

# Check that the vulnerability now has the most recent summary
vulnerability.refresh_from_db()
self.assertEqual(vulnerability.summary, "Second matching advisory")
Loading
0