Skip to content

fix(importer): sanitize HTML anchor tags from vulnerability details #4552

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.

Sign up for GitHub

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

Closed
biplavbarua wants to merge 1 commit into from
+12 −0
Closed

fix(importer): sanitize HTML anchor tags from vulnerability details #4552

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 12 additions & 0 deletions osv/sources.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
import hashlib
import logging
import os
import re

import jsonschema
import pygit2
Expand Down Expand Up @@ -178,6 +179,11 @@ def parse_vulnerability_from_dict(data, key_path=None, strict=False):
if not vulnerability.id:
raise ValueError('Missing id field. Invalid vulnerability.')

if vulnerability.summary:
vulnerability.summary = _sanitize_string(vulnerability.summary)
if vulnerability.details:
vulnerability.details = _sanitize_string(vulnerability.details)

return vulnerability


Expand Down Expand Up @@ -230,6 +236,12 @@ def _write_vulnerability_dict(data, output_path,
os.utime(output_path, (modified_date_timestamp, modified_date_timestamp))


def _sanitize_string(text):
"""Sanitize string by removing anchor tags."""
# Remove <a href="...">text</a> and keep text.
return re.sub(r'<a [^>]*>(.*?)</a>', r'\1', text, flags=re.IGNORECASE | re.DOTALL)


def write_vulnerability(vulnerability: vulnerability_pb2.Vulnerability,
output_path,
key_path=None):
Expand Down