CVSS 4.0
7.7 highCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:NHigh (7.7) in langchain-ai langchain-community. EPSS 0.6% estimated probability of exploitation activity in the next 30 days.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:NCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:NExplain CVE-2026-72848 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-72848?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-72848?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-72848 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.
From the CNA's record in the CVE List.
| Product | Affected |
|---|---|
| langchain-ai langchain-community | through 0.4.2 |
Red Hat rates this Important.
Red Hat rates this vulnerability as an Important severity flaw because remote exploitation can bypass perimeter isolation to read internal services or cloud metadata without requiring credentials. In Red Hat AI and automation environments, workloads that ingest external web documentation using langchain-community can be tricked into disclosing sensitive intranet resources via unvalidated nested sitemap links. Workloads that only parse trusted, pre-approved data sources or do not expose sitemap loading capabilities to external input are not vulnerable.
| Product | Package | State | Advisory |
|---|---|---|---|
| Red Hat OpenShift AI 3.4 | rhoai/odh-llama-stack-core-rhel9:1790958470 | Fixed 2026-10-19 | RHSA-2026:84734 |
| Red Hat OpenShift AI 3.4 | rhoai/odh-trustyai-nemo-guardrails-server-rhel9:1791556128 | Fixed 2026-10-19 | RHSA-2026:84734 |
| Exploit Intelligence | exploit-intelligence-tech-preview/vulnerability-analysis-rhel9 | Will not fix | |
| Exploit Intelligence | exploit-intelligence/vulnerability-analysis-rhel9 | Affected | |
| Migration Toolkit for Applications 8 | mta/mta-solution-server-rhel9 | Not affected | |
| OpenShift Lightspeed | openshift-lightspeed/lightspeed-service-api-rhel9 | Will not fix | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-25/lightspeed-chatbot-rhel8 | Will not fix | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-cuda-rhel9 | Affected | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-gaudi-rhel9 | Will not fix | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-rocm-rhel9 | Affected | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/disk-image-cuda-rhel9 | Affected |
Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-72848.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.