Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…

CVE-2026-72848: Server-Side Request Forgery (SSRF) in langchain-ai langchain-community

0
High
VulnerabilityCVE-2026-72848cvecve-2026-72848
Published: 08/20/2026 (08/20/2026, 21:57:36 UTC)
Source: CVE Database V5
Vendor/Project: langchain-ai
Product: langchain-community

Description

CVE-2026-72848 is a Server-Side Request Forgery (SSRF) vulnerability in the SitemapLoader component of langchain-community. The vulnerability arises because the restrict_to_same_domain control is only applied to leaf URLs, while nested sitemap elements are fetched without domain checks. This allows an attacker controlling or influencing a sitemap to cause the server to fetch internal or private network resources. The fetched internal content is then parsed and returned to the attacker, leading to potential information disclosure. The vulnerability affects langchain-community versions up to and including 0.4.2. No official patch or remediation guidance is currently available.

CVSS v3.1

Score 8.6high

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Changed
Confidentiality
High
Integrity
None
Availability
None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N

Affected software

langchain-community
pkg:pypi/langchain-community
Affected versions
<=0.4.2

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 08/20/2026, 22:22:13 UTC

Technical Analysis

The vulnerability exists in langchain_community/document_loaders/sitemap.py within the SitemapLoader.parse_sitemap method. While restrict_to_same_domain is intended to limit outbound requests to the same domain, it is only enforced on leaf URL entries. Nested sitemap elements bypass this restriction and are passed directly to the scrape_all method, which performs an aiohttp GET request without verifying the domain or blocking private, loopback, or link-local addresses. Consequently, an attacker who can supply or influence a nested sitemap URL can induce the server to fetch internal network resources. The content retrieved from these internal requests is parsed and included in the returned Documents, resulting in disclosure of internal responses to the attacker. This SSRF vulnerability has a CVSS 3.1 score of 8.6, indicating high severity. The affected versions are langchain-community <=0.4.2. No vendor advisory or patch is currently available, and no known exploits are reported in the wild.

Potential Impact

An attacker who controls or influences an ingested sitemap can exploit this vulnerability to make the server perform HTTP GET requests to internal or private network addresses that are normally inaccessible externally. The server will parse and return the fetched internal content to the attacker, leading to disclosure of potentially sensitive internal information. This bypasses the intended restrict_to_same_domain control, which was meant to confine outbound requests to the same domain. There is no indication that the vulnerability allows modification or disruption of internal resources, only information disclosure.

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should avoid ingesting sitemaps from untrusted or attacker-controlled sources. Consider implementing additional network-level controls to restrict outbound HTTP requests from the application server to trusted domains only. Monitor for updates from the langchain-ai project regarding patches or official mitigations.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-08-10T15:14:51.468Z
Cvss Version
3.1
State
PUBLISHED
Remediation Level
null

Threat ID: 6a877ac9acd9273b49302630

Added to database: 08/20/2026, 22:08:09 UTC

Last enriched: 08/20/2026, 22:22:13 UTC

Last updated: 08/20/2026, 22:22:13 UTC

Views: 4

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses