Skip to content

harden: add path validation in import-blogs.py (CWE-22) #683

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

Open
anupamme wants to merge 1 commit into
base: main
Choose a base branch
from
Open

harden: add path validation in import-blogs.py (CWE-22) #683

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
11 changes: 8 additions & 3 deletions utils/import-blogs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
#!/usr/bin/env python3

import os
import re
import sys
import yaml
import hashlib
Expand All @@ -15,7 +16,7 @@

def download(url):
print("downloading", url, file=sys.stderr)
resp = requests.get(url)
resp = requests.get(url, timeout=30)
if resp.status_code == 404:
print("error 404: %r" % url, file=sys.stderr)
return b""
Expand All @@ -24,13 +25,17 @@ def download(url):


def cached_download(url):
cache = os.path.join("cache", hashlib.sha256(url.encode("utf8")).hexdigest())
digest = hashlib.sha256(url.encode("utf8")).hexdigest()
if not re.fullmatch(r"[0-9a-f]{64}", digest):
raise ValueError("invalid cache digest")
cache = os.path.join("cache", digest)
cache_url_meta = os.path.join("cache", digest + ".url")
if not os.path.exists(cache):
os.makedirs("cache", exist_ok=True)
data = download(url)
with open(cache, "wb") as fh:
fh.write(data)
with open(cache + ".url", "wb") as fh:
with open(cache_url_meta, "wb") as fh:
fh.write(url.encode("utf8"))
with open(cache, "rb") as fh:
return fh.read()
Expand Down