Security readout for executives and security teams
Plain-English summary
Applications using vulnerable LangChain Core prompt loaders may let an unauthenticated attacker read sensitive host files when prompt configurations are influenced by users. The flaw threatens confidentiality, including secrets and application data, but the cited sources do not indicate file modification or service disruption. Version 1.2.22 contains the patch.
Executive priority
Prioritize remediation for internet-facing or multi-tenant applications that accept externally influenced prompt configurations. Upgrade promptly and assess possible secret exposure. Lower the immediate priority only when teams verify that affected functions are unused or all configurations are trusted and tightly constrained.
Technical view
Before LangChain Core 1.2.22, legacy load_prompt() and load_prompt_from_config() paths in langchain_core.prompts.loading insufficiently validate filenames from deserialized configuration dictionaries. Directory traversal or absolute paths can expose arbitrary readable host files. Extension checks limit template reads to .txt and example files to .json or .yaml; CVSS 3.1 is 7.5 (CWE-22).
Likely exposure
Exposure requires LangChain Core earlier than 1.2.22 and an application path that passes user-influenced prompt configurations into the affected legacy loaders. Risk is highest for network-facing services where untrusted users can control embedded file paths. Installation alone does not establish exploitability.
Exploitation context
The CVSS vector describes network-reachable, low-complexity exploitation requiring neither privileges nor user interaction, with high confidentiality impact. However, the bundle marks this CVE as absent from KEV, and no supplied source establishes active exploitation. Treat exploitation status as unconfirmed.
Researcher notes
The vulnerability is a path-validation failure during prompt configuration deserialization. Practical impact depends on application data flow and runtime file permissions. Extension restrictions narrow readable targets but do not eliminate sensitive-file exposure. The supplied evidence supports confidentiality loss only; it does not establish integrity or availability impact, public proof-of-concept availability, or observed attacks.
Mitigation direction
- Upgrade LangChain Core to version 1.2.22 or later.
- Identify and restrict user influence over configurations passed to the affected legacy prompt loaders.
- Replace legacy loading paths where feasible and accept only explicitly approved files.
- Reduce the application account's filesystem access to necessary files only.
- Review relevant Red Hat advisories when using affected downstream packages.
Validation and detection
- Inventory deployed LangChain Core versions and flag releases earlier than 1.2.22.
- Trace calls to load_prompt() and load_prompt_from_config() from untrusted inputs.
- Confirm prompt configuration paths are constrained to approved directories and files.
- Verify the runtime identity cannot read unnecessary secrets or sensitive data.
- After upgrading, confirm version 1.2.22 or later is present in deployed artifacts.
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-2026:59159CVE 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.