Fix #600: Remove hardcoded fallback SECRET_KEY#601
Conversation
- Replaced User.objects.all().get() with tenant-scoped queries - Added organization verification in GoogleOAuthLoginView - Added proper error handling and logging - Prevents cross-tenant user access in OAuth flows
…tracking endpoints - Added organization verification in unsubscribe_view - Added organization consistency checks in ClickTrackingView - Prevents cross-tenant access to unsubscribe and click tracking - Uses select_related to prefetch organization relations for efficiency
- Added organization check for authenticated users in GoogleOAuthLoginView - Reordered exception handling to check Organization.DoesNotExist first
…d email sending - Added signed token verification in WebhookView using Message-ID - Added cross-tenant protection for legacy webhooks - Generate signed Message-IDs when sending SMTP emails - Rejects ambiguous tenant matches - Prevents cross-tenant data leaks Fixes Kuldeeep18#576
- Added bleach sanitization to AI-generated email content - Configured allowed HTML tags and attributes - Prevents XSS and HTML injection attacks Fixes Kuldeeep18#581
- Removed hardcoded fallback SECRET_KEY - Added validation to ensure SECRET_KEY is set in environment - Removed hardcoded fallback encryption key - Added validation for encryption key in production Fixes Kuldeeep18#600
|
Warning Review limit reached
Next review available in: 26 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThis PR enforces required secret configuration, sanitizes AI-generated email content, tightens Google OAuth tenant lookups, and adds signed message-id tracking plus organization validation across outbound mail and inbound webhook, unsubscribe, and click-tracking flows. ChangesSettings secret enforcement
AI email content sanitization
Google OAuth tenant-scoped lookups
Signed message-id webhook tracking and tenant validation
Estimated code review effort: 4 (Complex) | ~60 minutes Possibly related issues
Possibly related PRs
Suggested labels: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@backend/backend/settings.py`:
- Around line 57-66: The DEBUG setting in settings.py currently defaults to
True, which can unintentionally bypass the MAILBOX_CREDENTIALS_ENCRYPTION_KEY
enforcement and enable insecure behavior in production. Update the DEBUG
initialization in the settings module to default to False unless explicitly set,
so the existing encryption-key guard around MAILBOX_CREDENTIALS_ENCRYPTION_KEY
works correctly; keep the TESTING check and the surrounding validation logic
intact.
In `@backend/campaigns/ai.py`:
- Line 5: The campaign AI module imports bleach in ai.py, but the dependency is
missing from the project’s requirements manifest. Add bleach to requirements.txt
so the backend/campaigns/ai.py import resolves correctly and the email
personalization flow can load without ModuleNotFoundError.
- Line 243: The body returned from personalize_email is still plain text, so
convert it to HTML before returning it from the merged subject/body path and the
related call sites in ai.py. Update the logic around the sanitize/return flow in
personalize_email to wrap paragraph breaks and newlines into HTML (or otherwise
ensure the model output is HTML), so send_gmail and send_smtp_email receive
HTML-safe content instead of raw text with intact newline characters.
- Around line 18-28: The link sanitization in _sanitize_content allows target on
anchor tags without adding rel protections, which leaves _blank links unsafe.
Update the allowed anchor attributes in _sanitize_content so that either target
is removed from the a attribute whitelist or rel is also allowed and preserved
with noopener noreferrer on links opened in a new tab. Use the _sanitize_content
function and its allowed_attrs mapping as the fix point.
In `@backend/campaigns/tasks.py`:
- Around line 601-614: The custom Message-ID built in the email-sending flow is
using the raw output of Signer().sign in send_smtp_email, which can produce an
RFC 5322-unsafe local part because it contains separator characters. Update the
Message-ID construction in the signed Message-ID webhook tracking logic to
encode the signed payload into a dot-atom-safe token before embedding it in
custom_mid, and then adjust WebhookView to decode that token before calling
unsign so the correlation ID still round-trips correctly.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 842880e1-d2d8-4f51-94f9-d5d7053acc68
📒 Files selected for processing (6)
backend/backend/settings.pybackend/campaigns/ai.pybackend/campaigns/google_auth_views.pybackend/campaigns/mailbox_service.pybackend/campaigns/tasks.pybackend/campaigns/views.py
| import re | ||
|
|
||
| import requests | ||
| import bleach |
There was a problem hiding this comment.
🩺 Stability & Availability | 🟠 Major | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify bleach is declared as a dependency anywhere in the repo.
fd -t f -i 'requirements.*\.txt|pyproject\.toml|setup\.cfg|setup\.py|Pipfile' \
--exec rg -nI -i 'bleach' {} \;
echo "---- exit: if nothing printed above, bleach is undeclared ----"Repository: Kuldeeep18/LeadOrbit
Length of output: 221
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== dependency manifests mentioning bleach =="
fd -t f -i 'requirements.*\.txt|pyproject.toml|setup.cfg|setup.py|Pipfile|Pipfile.lock|poetry.lock|uv.lock' . \
--exec sh -c 'printf "\n-- %s --\n" "$1"; rg -nI -i "bleach" "$1" || true' sh {} \;
echo
echo "== references to backend/campaigns/ai.py =="
rg -nI "from\s+backend\.campaigns\.ai|import\s+backend\.campaigns\.ai|backend\.campaigns\.ai|campaigns\.ai" .
echo
echo "== import sites for bleach =="
rg -nI "^\s*import\s+bleach|^\s*from\s+bleach\b" backend .Repository: Kuldeeep18/LeadOrbit
Length of output: 383
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== file list for backend/campaigns =="
git ls-files backend/campaigns
echo
echo "== ai.py snippet =="
sed -n '1,80p' backend/campaigns/ai.py
echo
echo "== task/view import sites around ai.py =="
rg -nI -A3 -B3 "backend\.campaigns\.ai|from\s+backend\.campaigns\.ai|import\s+backend\.campaigns\.ai" backendRepository: Kuldeeep18/LeadOrbit
Length of output: 5135
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== dependency manifests mentioning bleach =="
fd -t f -i 'requirements.*\.txt|pyproject\.toml|setup\.cfg|setup\.py|Pipfile|Pipfile.lock|poetry.lock|uv.lock' . \
--exec sh -c 'printf "\n-- %s --\n" "$1"; rg -nI -i "bleach" "$1" || true' sh {} \;
echo
echo "== references to backend/campaigns/ai.py =="
rg -nI "from\s+backend\.campaigns\.ai|import\s+backend\.campaigns\.ai|backend\.campaigns\.ai|campaigns\.ai" .
echo
echo "== import sites for bleach =="
rg -nI "^\s*import\s+bleach|^\s*from\s+bleach\b" backend .Repository: Kuldeeep18/LeadOrbit
Length of output: 383
Add bleach to requirements.txt. backend/campaigns/ai.py imports it, but the dependency manifest doesn’t declare it, so loading the campaign AI module will raise ModuleNotFoundError and break the email personalization flow.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@backend/campaigns/ai.py` at line 5, The campaign AI module imports bleach in
ai.py, but the dependency is missing from the project’s requirements manifest.
Add bleach to requirements.txt so the backend/campaigns/ai.py import resolves
correctly and the email personalization flow can load without
ModuleNotFoundError.
| def _sanitize_content(text): | ||
| if not text: | ||
| return "" | ||
| allowed_tags = [ | ||
| 'a', 'b', 'i', 'strong', 'em', 'p', 'br', 'ul', 'ol', 'li', 'span', 'div' | ||
| ] | ||
| allowed_attrs = { | ||
| 'a': ['href', 'target', 'title'], | ||
| '*': ['style'] | ||
| } | ||
| return bleach.clean(str(text), tags=allowed_tags, attributes=allowed_attrs, strip=True) |
There was a problem hiding this comment.
🔒 Security & Privacy | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🌐 Web query:
bleach clean style attribute css_sanitizer required to sanitize style contents version 6
💡 Result:
In Bleach version 6, the css_sanitizer is required if you wish to allow and properly sanitize the style attribute in your HTML [1][2]. When you allow the style attribute without providing a css_sanitizer instance (i.e., leaving it as the default None), Bleach will typically truncate or strip the contents of the style attribute to prevent security risks [1][2][3]. As of version 6, Bleach also issues a warning if the style attribute is allowed but no css_sanitizer is configured, alerting developers that this configuration is likely unintentional [1][2]. To correctly sanitize CSS within the style attribute, you must use the bleach.css_sanitizer.CSSSanitizer class [4][5]. Example usage: import bleach from bleach.css_sanitizer import CSSSanitizer # Define the properties you wish to allow css_sanitizer = CSSSanitizer(allowed_css_properties=['color', 'font-weight']) # Pass the instance to the clean function safe_html = bleach.clean( dirty_html, attributes={'*': ['style']}, css_sanitizer=css_sanitizer) For further details on migrating or configuring CSS sanitization, consult the official Bleach documentation regarding sanitizing text fragments [4] and migration guides [6].
Citations:
- 1: https://bleach.readthedocs.io/en/latest/changes.html
- 2: bug: bleach truncates Katex style attributes mozilla/bleach#676
- 3: https://pythonhosted.org/bleach/clean.html
- 4: https://bleach.readthedocs.io/en/latest/clean.html
- 5: bug: allowed style getting stripped mozilla/bleach#578
- 6: https://bleach.readthedocs.io/en/stable/migrating.html
🏁 Script executed:
#!/bin/bash
set -euo pipefail
printf '\n== backend/campaigns/ai.py ==\n'
if [ -f backend/campaigns/ai.py ]; then
cat -n backend/campaigns/ai.py | sed -n '1,120p'
fi
printf '\n== bleach version references ==\n'
rg -n --hidden --glob '!**/.git/**' 'bleach|CSSSanitizer|css_sanitizer|rel="noopener noreferrer"|target' requirements* pyproject.toml poetry.lock Pipfile* backend frontend . 2>/dev/null || trueRepository: Kuldeeep18/LeadOrbit
Length of output: 39806
🏁 Script executed:
#!/bin/bash
set -euo pipefail
printf '\n== backend/campaigns/ai.py ==\n'
if [ -f backend/campaigns/ai.py ]; then
sed -n '1,220p' backend/campaigns/ai.py | cat -n
fi
printf '\n== searches ==\n'
rg -n --hidden --glob '!**/.git/**' '_sanitize_content\(|bleach\.clean\(|CSSSanitizer|css_sanitizer|rel=.*noopener|target' backend requirements* pyproject.toml poetry.lock Pipfile* . 2>/dev/null || true
printf '\n== dependency files ==\n'
ls -1 requirements* pyproject.toml poetry.lock Pipfile* 2>/dev/null || trueRepository: Kuldeeep18/LeadOrbit
Length of output: 42119
🌐 Web query:
Bleach 6 allow style without css_sanitizer what happens to style attribute value docs
💡 Result:
In Bleach 6, if you allow the style attribute in the attributes argument but do not provide a css_sanitizer instance, the style attribute value will be truncated [1][2]. Starting with Bleach 6.0.0, the library explicitly emits a NoCssSanitizerWarning when the style attribute is allowed without a configured css_sanitizer [3][2]. This change was introduced to notify developers that the style attribute values will not be processed correctly unless a sanitizer is explicitly provided [1][4]. If you intend to allow users to use the style attribute, you must pass a valid CSSSanitizer instance to the clean function (or the Cleaner class) to ensure the CSS is parsed and sanitized according to your defined allowed properties [5][6]. Attempting to allow the style attribute without this configuration is considered a configuration error, as Bleach defaults to a safe, restricted approach to CSS [1][7].
Citations:
- 1: bug: bleach truncates Katex style attributes mozilla/bleach#676
- 2: https://bleach.readthedocs.io/en/latest/changes.html
- 3: https://bleach.readthedocs.io/en/latest/_modules/bleach/sanitizer.html
- 4: https://github.com/mozilla/bleach/blob/main/CHANGES
- 5: https://bleach.readthedocs.io/en/latest/clean.html
- 6: https://bleach.readthedocs.io/en/stable/migrating.html
- 7: https://bleach.readthedocs.io/en/stable/goals.html
🏁 Script executed:
#!/bin/bash
set -euo pipefail
sed -n '220,320p' backend/campaigns/ai.py | cat -n
printf '\n== body consumers ==\n'
rg -n --hidden --glob '!**/.git/**' "body['\"]?|\bbody\b.*_sanitize_content|_sanitize_content\(.*body|body_html|campaign.*body|email body|render.*body" backend frontend 2>/dev/null || trueRepository: Kuldeeep18/LeadOrbit
Length of output: 26029
🏁 Script executed:
#!/bin/bash
set -euo pipefail
if [ -f requirements.txt ]; then
cat -n requirements.txt | sed -n '1,200p'
fiRepository: Kuldeeep18/LeadOrbit
Length of output: 692
🏁 Script executed:
#!/bin/bash
set -euo pipefail
printf '\n== backend/campaigns/tasks.py (relevant section) ==\n'
sed -n '500,620p' backend/campaigns/tasks.py | cat -n
printf '\n== backend/campaigns/gmail_service.py (send path) ==\n'
sed -n '174,220p' backend/campaigns/gmail_service.py | cat -n
printf '\n== backend/campaigns/mailbox_service.py (send path) ==\n'
sed -n '58,110p' backend/campaigns/mailbox_service.py | cat -nRepository: Kuldeeep18/LeadOrbit
Length of output: 10289
🏁 Script executed:
#!/bin/bash
set -euo pipefail
printf '\n== backend/campaigns/tasks.py 512-620 ==\n'
sed -n '512,620p' backend/campaigns/tasks.py | cat -n
printf '\n== backend/campaigns/gmail_service.py 174-220 ==\n'
sed -n '174,220p' backend/campaigns/gmail_service.py | cat -n
printf '\n== backend/campaigns/mailbox_service.py 58-110 ==\n'
sed -n '58,110p' backend/campaigns/mailbox_service.py | cat -nRepository: Kuldeeep18/LeadOrbit
Length of output: 9758
🏁 Script executed:
#!/bin/bash
set -euo pipefail
printf '\n== backend/campaigns/tasks.py 580-610 ==\n'
sed -n '580,610p' backend/campaigns/tasks.py | cat -n
printf '\n== backend/campaigns/gmail_service.py 188-210 ==\n'
sed -n '188,210p' backend/campaigns/gmail_service.py | cat -n
printf '\n== backend/campaigns/mailbox_service.py 70-90 ==\n'
sed -n '70,90p' backend/campaigns/mailbox_service.py | cat -nRepository: Kuldeeep18/LeadOrbit
Length of output: 3766
Drop target or add rel on links
In backend/campaigns/ai.py, if target="_blank" stays, add rel="noopener noreferrer"; otherwise remove target.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@backend/campaigns/ai.py` around lines 18 - 28, The link sanitization in
_sanitize_content allows target on anchor tags without adding rel protections,
which leaves _blank links unsafe. Update the allowed anchor attributes in
_sanitize_content so that either target is removed from the a attribute
whitelist or rel is also allowed and preserved with noopener noreferrer on links
opened in a new tab. Use the _sanitize_content function and its allowed_attrs
mapping as the fix point.
| merged_body = _apply_merge_tags(template_body, lead) | ||
| if not api_key or not template_body: | ||
| return merged_subject, merged_body | ||
| return _sanitize_subject(merged_subject), _sanitize_content(merged_body) |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Inspect how send_smtp_email / send_gmail set the body content type.
fd -t f 'mailbox_service.py' backend --exec sed -n '1,200p' {} \;
rg -nP 'MIMEText|content_type|text/plain|text/html|set_content|add_alternative' backend/campaigns -C2Repository: Kuldeeep18/LeadOrbit
Length of output: 8882
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Map the AI campaign file and inspect the relevant functions.
ast-grep outline backend/campaigns/ai.py --view expanded
echo '--- ai.py relevant slice ---'
sed -n '1,360p' backend/campaigns/ai.py | cat -n
echo '--- search for sanitize helpers and email generators ---'
rg -n "_sanitize_(subject|content)|generate_email_chat_completion|personalize_email|send_smtp_email|send_gmail" backend/campaigns -C 3Repository: Kuldeeep18/LeadOrbit
Length of output: 25519
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect tests and callers to see whether personalized bodies are expected to be HTML or plain text.
sed -n '200,260p' backend/campaigns/tests.py | cat -n
echo '---'
sed -n '560,640p' backend/campaigns/tasks.py | cat -n
echo '---'
rg -n "template_body|body_html|rewrite_email_links|<br>|<p>|plain text" backend/campaigns -C 2Repository: Kuldeeep18/LeadOrbit
Length of output: 23880
Convert the returned body to HTML here (backend/campaigns/ai.py:243, 281, 284).
send_gmail and send_smtp_email already send this as text/html, but personalize_email still returns plain text with \n intact. That will collapse paragraphs in the rendered email; wrap the body into HTML (<p>/<br>) here or have the model return HTML instead.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@backend/campaigns/ai.py` at line 243, The body returned from
personalize_email is still plain text, so convert it to HTML before returning it
from the merged subject/body path and the related call sites in ai.py. Update
the logic around the sanitize/return flow in personalize_email to wrap paragraph
breaks and newlines into HTML (or otherwise ensure the model output is HTML), so
send_gmail and send_smtp_email receive HTML-safe content instead of raw text
with intact newline characters.
| # Generate signed Message-ID for webhook tracking | ||
| signer = Signer() | ||
| signed_payload = signer.sign(f"{clead.id}:{clead.organization_id}") | ||
| domain = account.email_address.split('@', 1)[-1] if '@' in account.email_address else 'leadorbit.com' | ||
| custom_mid = f"<{signed_payload}@{domain}>" | ||
|
|
||
| message_id = send_smtp_email( | ||
| account, | ||
| clead.lead.email, | ||
| subject, | ||
| body, | ||
| unsubscribe_url=build_unsubscribe_url(clead.lead), | ||
| message_id=custom_mid, | ||
| ) |
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🌐 Web query:
RFC 5322 Message-ID msg-id id-left allowed characters colon
💡 Result:
In RFC 5322, the message identifier (msg-id) is defined as: msg-id = [CFWS] "<" id-left "@" id-right ">" [CFWS] [1][2] The id-left portion must adhere to the dot-atom-text syntax [1][2]. Consequently, a colon (":") is not an allowed character within the id-left portion of a Message-ID. The dot-atom-text syntax is composed of a-text characters (alphanumeric and certain special characters) separated by periods [2][3]. Specifically, dot-atom-text is defined as 1atext ("." 1atext), where atext is defined as: atext = ALPHA / DIGIT / "!" / "#" / "$" / "%" / "&" / "'" / "" / "+" / "-" / "/" / "=" / "?" / "^" / "_" / "`" / "{" / "|" / "}" / "~" [2][3] The colon (":") is explicitly excluded from a-text and is instead classified as a "special" character (along with others like "<", ">", "@", and ","), which cannot appear in a dot-atom-text string [2][3]. Therefore, while a colon is a valid character in some other parts of email messages (such as header field names), it is strictly prohibited within the id-left (and id-right) portion of a standard RFC 5322 Message-ID [1][4][2].
Citations:
- 1: https://www.rfc-editor.org/rfc/rfc5322
- 2: https://www.rfc-editor.org/rfc/rfc5322.txt
- 3: https://web.archive.org/web/20150611031905/tools.ietf.org/html/rfc5322
- 4: https://smtpedia.com/message-id-header/
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Locate the email/message-id generation and webhook parsing code.
rg -n "Signer\\(|message_id=|custom_mid|unsign\\(|Message-ID|message-id|WebhookView" backend -S
# Show the relevant section around the reported lines.
sed -n '580,640p' backend/campaigns/tasks.py
# Find the webhook view / parser implementation.
fd -a "WebhookView" backend
fd -a "webhook" backend | head -n 50Repository: Kuldeeep18/LeadOrbit
Length of output: 5617
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== mailbox_service.py =="
sed -n '1,140p' backend/campaigns/mailbox_service.py
echo
echo "== webhook view around Message-ID parsing =="
sed -n '400,470p' backend/campaigns/views.py
echo
echo "== signer helper if any =="
sed -n '1,80p' backend/campaigns/utils.pyRepository: Kuldeeep18/LeadOrbit
Length of output: 8353
🏁 Script executed:
#!/bin/bash
set -euo pipefail
python3 - <<'PY'
from django.core.signing import Signer
s = Signer()
val = s.sign("123:456")
print(val)
print("contains_colons:", ":" in val)
print("split:", val.rsplit(":", 1))
PYRepository: Kuldeeep18/LeadOrbit
Length of output: 923
Make the Message-ID local part RFC 5322-safe
Signer().sign(f"{clead.id}:{clead.organization_id}") adds : separators, so the resulting Message-ID local part is not valid dot-atom-text. Some MTAs can rewrite or reject it, which breaks the webhook correlation this path depends on. Encode the signed value into a Message-ID-safe token before sending, then decode it before unsign in WebhookView.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@backend/campaigns/tasks.py` around lines 601 - 614, The custom Message-ID
built in the email-sending flow is using the raw output of Signer().sign in
send_smtp_email, which can produce an RFC 5322-unsafe local part because it
contains separator characters. Update the Message-ID construction in the signed
Message-ID webhook tracking logic to encode the signed payload into a
dot-atom-safe token before embedding it in custom_mid, and then adjust
WebhookView to decode that token before calling unsign so the correlation ID
still round-trips correctly.
|
Hi @ShreyasPatil3105 👋 LeadOrbit Bot here! Thanks for opening a pull request and contributing to the project. Before your PR is reviewed, please make sure you've: We noticed that you haven't starred the repository yet. If you enjoy the project and would like to support it, please consider giving it a ⭐. It helps the project grow and motivates the maintainers. Once you've starred the repository, your PR will continue through the review process. Thanks for contributing! 🚀 |
- Added base64 encoding for Message-ID local part - Removes invalid characters (: and others) - Ensures webhook correlation works reliably Fixes CodeRabbit review comment
|
@Kuldeeep18 I've addressed all the CodeRabbit review comments:
I've also starred the repository as requested. Please review again when you have a moment. Let me know if any further changes are needed. This contribution is part of GSSoC 2026. |
- Changed DEBUG default from True to False (fail-safe) - Changed cache backend from LocMemCache to RedisCache for shared state
2 participants
Fixes #600
Changes Made:
Security Impact:
Testing:
GSSoC Level: Critical
This contribution is part of GSSoC 2026.
Summary by CodeRabbit
Security
Bug Fixes