LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
CVE-2026-34070
This high-severity CVE scores 7.5 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 1.2%, top 34% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
- High severity, but no confirmed exploitation yet
A fix is available — apply it.
- CVSS v3
- 7.5
- EG Score
- 7.5(medium)
- EG Risk
- 65(Attend)EG Risk 65/100SSVC: Attend
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity75% × 45%Exploitation40% × 40%Automatability100% × 15%Action: Remediate soon — notable exploitation risk. - EPSS PROB
- 1%
- EPSS %ILE
- 71%
- KEV
- Not listed
Published
March 31, 2026
Last Modified
August 25, 2026
Advisory Details (3)
Auto-updated Jun 10, 2026Path traversal in legacy `load_prompt` functions in `langchain-core` (CWE-22) · Advisory · langchain-ai/langchain · GitHub
https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54langchain-core==1.2.22
Patch available: langchain-ai/langchain langchain-core==1.2.22
https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22commit 27add913474e (langchain-ai/langchain)
Patch available: langchain-ai/langchain langchain==1.3.0a2 (contains commit 27add913474e)
https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47cVendor Advisories for CVE-2026-34070(3)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
- RHSA-2026:59159Red Hat Product SecurityHigh
Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.5 Container Release Update
- RHSA-2026:37275Red Hat Product SecurityCritical
Red Hat Security Advisory: RHOAI 3.3.5 - Red Hat OpenShift AI
- RHSA-2026:24766Red Hat Product SecurityHigh
Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.5 Container Release Update
Patch Availability(3)
| Vendor / Ecosystem | Fixed in / Patch | Released | Source |
|---|---|---|---|
| redhat | ansible-automation-platform-25/lightspeed-rhel8:1787229385 | 2026-08-24 | redhat |
| redhat | rhoai/odh-trustyai-nemo-guardrails-server-rhel9:1782471606 | 2026-07-09 | redhat |
| redhat | ansible-automation-platform-25/lightspeed-rhel8:1780082949 | 2026-06-09 | redhat |
Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.
Affected Packages
(1 across 1 ecosystem)
PyPI(1)
| Package | Vulnerable range | Fixed in | Dependents |
|---|---|---|---|
| langchain-core | 0.0.1 ... 1.2.9 (264 versions) | 1.2.22 | — |
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 8× in last 7d / 35× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
Showing the most recent 100 of 183 total refreshes for this CVE.
- 2026-09-15 03:11 UTCEPSS rescore
- 2026-09-13 16:47 UTCEPSS rescore
- 2026-09-13 11:54 UTCOSV refresh
- 2026-09-12 15:01 UTCEPSS rescore
- 2026-09-11 14:53 UTCEPSS rescore
- 2026-09-11 09:37 UTCEPSS rescore
- 2026-09-10 09:34 UTCEPSS rescore
- 2026-09-08 22:00 UTCEPSS rescore
- 2026-09-07 16:01 UTCEPSS rescore
- 2026-09-06 13:47 UTCEPSS rescore
- 2026-09-04 05:06 UTCEPSS rescore
- 2026-09-02 14:12 UTCEPSS rescore
- 2026-09-01 13:53 UTCEPSS rescore
- 2026-09-01 04:39 UTCEPSS rescore
- 2026-08-30 19:17 UTCEPSS rescore
- 2026-08-30 01:22 UTCEPSS rescore
- 2026-08-28 21:41 UTCEPSS rescore
- 2026-08-27 14:25 UTCEPSS rescore
- 2026-08-26 14:46 UTCEPSS rescore
- 2026-08-25 13:49 UTCEPSS rescore
- 2026-08-25 13:25 UTCEG score recompute
- 2026-08-25 13:25 UTCVendor advisory
- 2026-08-25 12:22 UTCEG score recompute
- 2026-08-25 12:22 UTCVendor advisory
- 2026-08-24 14:17 UTCEPSS rescore
Show 75 moreShow fewer
- 2026-08-23 00:19 UTCEPSS rescore
- 2026-08-21 23:49 UTCEPSS rescore
- 2026-08-20 22:55 UTCEPSS rescore
- 2026-08-20 22:55 UTCEPSS rescore
- 2026-08-19 17:03 UTCEPSS rescore
- 2026-08-18 13:48 UTCEPSS rescore
- 2026-08-17 13:47 UTCEPSS rescore
- 2026-08-16 14:56 UTCEPSS rescore
- 2026-08-16 09:42 UTCEG score recompute
- 2026-08-16 09:42 UTCVendor advisory
- 2026-08-16 02:14 UTCEPSS rescore
- 2026-08-15 01:30 UTCEPSS rescore
- 2026-08-14 19:07 UTCVendor advisory
- 2026-08-14 06:06 UTCEG score recompute
- 2026-08-14 06:06 UTCVendor advisory
- 2026-08-13 22:00 UTCEPSS rescore
- 2026-08-12 20:26 UTCEG score recompute
- 2026-08-12 20:26 UTCVendor advisory
- 2026-08-12 13:50 UTCEPSS rescore
- 2026-08-11 20:39 UTCEG score recompute
- 2026-08-11 20:39 UTCVendor advisory
- 2026-08-11 03:39 UTCEG score recompute
- 2026-08-11 03:39 UTCVendor advisory
- 2026-08-11 00:00 UTCEPSS rescore
- 2026-08-10 06:43 UTCVendor advisory
- 2026-08-09 18:12 UTCEG score recompute
- 2026-08-09 18:12 UTCVendor advisory
- 2026-08-09 13:46 UTCEPSS rescore
- 2026-08-09 05:41 UTCEG score recompute
- 2026-08-09 05:41 UTCVendor advisory
- 2026-08-08 16:37 UTCEPSS rescore
- 2026-08-08 04:16 UTCEG score recompute
- 2026-08-08 04:16 UTCVendor advisory
- 2026-08-07 15:46 UTCVendor advisory
- 2026-08-06 18:13 UTCEG score recompute
- 2026-08-06 18:13 UTCVendor advisory
- 2026-08-06 13:46 UTCEPSS rescore
- 2026-08-06 00:38 UTCEG score recompute
- 2026-08-06 00:38 UTCVendor advisory
- 2026-08-05 19:17 UTCEPSS rescore
- 2026-08-04 15:10 UTCEPSS rescore
- 2026-08-04 10:38 UTCEPSS rescore
- 2026-08-03 22:58 UTCEG score recompute
- 2026-08-03 22:58 UTCVendor advisory
- 2026-08-03 10:36 UTCEPSS rescore
- 2026-08-02 15:00 UTCEG score recompute
- 2026-08-02 15:00 UTCVendor advisory
- 2026-08-02 02:27 UTCEPSS rescore
- 2026-08-01 04:16 UTCEPSS rescore
- 2026-07-30 16:28 UTCEPSS rescore
- 2026-07-30 01:30 UTCEPSS rescore
- 2026-07-27 14:13 UTCEPSS rescore
- 2026-07-26 14:54 UTCEPSS rescore
- 2026-07-26 14:54 UTCEPSS rescore
- 2026-07-25 14:18 UTCEPSS rescore
- 2026-07-25 14:18 UTCEPSS rescore
- 2026-07-24 14:17 UTCEPSS rescore
- 2026-07-24 14:17 UTCEPSS rescore
- 2026-07-23 14:18 UTCEPSS rescore
- 2026-07-23 14:18 UTCEPSS rescore
- 2026-07-23 03:09 UTCEG score recompute
- 2026-07-22 14:08 UTCEPSS rescore
- 2026-07-21 15:24 UTCEPSS rescore
- 2026-07-20 17:08 UTCEPSS rescore
- 2026-07-19 14:31 UTCEPSS rescore
- 2026-07-19 02:29 UTCEPSS rescore
- 2026-07-18 10:04 UTCEPSS rescore
- 2026-07-17 04:54 UTCOSV refresh
- 2026-07-16 17:03 UTCEPSS rescore
- 2026-07-15 16:57 UTCEPSS rescore
- 2026-07-15 16:57 UTCEPSS rescore
- 2026-07-15 02:00 UTCEPSS rescore
- 2026-07-13 22:30 UTCEPSS rescore
- 2026-07-12 05:46 UTCEPSS rescore
- 2026-07-11 08:27 UTCEPSS rescore
Frequently asked(5)
What is CVE-2026-34070?
When was CVE-2026-34070 disclosed?
Is CVE-2026-34070 actively exploited?
What is the CVSS score of CVE-2026-34070?
How do I remediate CVE-2026-34070?
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-34070
Is Your Infrastructure Affected by CVE-2026-34070?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.