Security readout for executives and security teams
Plain-English summary
CVE-2026-34070 lets a malicious user-influenced LangChain prompt configuration make an application read unintended local files. The impact is data exposure, not code execution, but secrets or configuration files could be exposed if the vulnerable loading functions are reachable.
Executive priority
Treat as high priority for AI applications that accept external prompt configuration. The business risk is unauthorized file disclosure from application hosts, especially where secrets or customer data are present.
Technical view
Before version 1.2.22, langchain_core.prompts.loading functions load_prompt() and load_prompt_from_config() accepted paths from deserialized config dictionaries without preventing directory traversal or absolute path injection. Reads are constrained by extension checks for templates and examples, but confidentiality impact is rated high.
Likely exposure
Exposure is likely limited to applications using affected LangChain versions before 1.2.22 and passing user-influenced prompt configurations into load_prompt() or load_prompt_from_config().
Exploitation context
The source bundle does not cite active exploitation, and KEV is false. Abuse requires a reachable application path where attacker-controlled or attacker-influenced prompt configuration is deserialized and loaded.
Researcher notes
Focus review on trust boundaries around prompt configuration deserialization. Extension checks reduce some paths but do not eliminate sensitive file disclosure risk for allowed .txt, .json, .yaml, or .yml-style prompt resources if reachable.
Mitigation direction
- Upgrade LangChain or langchain-core to version 1.2.22 or later.
- Stop passing user-influenced prompt configurations to legacy prompt loading functions.
- Restrict prompt file loading to approved directories and trusted configuration sources.
- Review Red Hat advisories if consuming LangChain through Red Hat products.
- Check vendor guidance for any additional downstream fixes or backports.
Validation and detection
- Inventory deployed LangChain and langchain-core versions across applications.
- Identify use of load_prompt() and load_prompt_from_config().
- Trace whether prompt configurations can be influenced by users or external systems.
- Confirm upgraded packages include the 1.2.22 fix or downstream backport.
- Review logs for unexpected prompt file-loading failures or unusual configuration inputs.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-22: File access and web shell behavior lookup
File traversal and upload weaknesses can lead teams to review file, web shell, execution, and collection telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupFile access behavior lookup
The CVE wording references file access or upload behavior, so file telemetry and web shell review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-34070 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- High
- CVSS
- 7.5 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
2 official scoresWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N3.93.6GitHub_MCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N3.93.6redhat-SADPVulnerability scoring details
Base CVSS 3.1 score
7.5HighVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Base CVSS 3.1 score
7.5HighVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- ADP timelineredhat-SADP
Made public.
- CVE publishedCVE Program
The CVE record was published.
- ADP timelineredhat-SADP
Reported to Red Hat.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
- 2026-03-31T03:02:19.523Z: Reported to Red Hat.
- 2026-03-31T02:01:49.320Z: Made public.
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54CVE reference, GitHub_M · x_refsource_CONFIRM
- https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47cCVE reference, GitHub_M · x_refsource_MISC
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22CVE reference, GitHub_M · x_refsource_MISC
- https://access.redhat.com/security/cve/CVE-2026-34070CVE reference, redhat-SADP · vdb-entry, x_refsource_REDHAT
- RHBZ#2453287CVE reference, redhat-SADP · issue-tracking, x_refsource_REDHAT
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34070.jsonCVE reference, redhat-SADP · x_sadp-csaf-vex
- https://access.redhat.com/errata/RHSA-2026:24766CVE reference, redhat-SADP · vendor-advisory, x_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:37275CVE reference, redhat-SADP · vendor-advisory, x_refsource_REDHAT
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.