Security readout for executives and security teams
Plain-English summary
This issue affects applications that use older LangSmith SDKs to pull public prompts from LangSmith Hub. A public prompt can carry externally controlled serialized manifest content, but vulnerable SDK versions did not clearly treat that content as untrusted. The business risk is unexpected model or LangChain object behavior in systems that import public prompts.
Executive priority
Treat as a high-priority dependency update for teams using LangSmith public prompt pulls. Urgency is highest where AI workflows import prompts from external owners into production or sensitive environments.
Technical view
Before LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, prompt pull methods deserialize prompt manifests from LangSmith Hub. For public owner/name pulls, an external party controls the manifest. The advisory maps this to CWE-502 and CVSS 7.1, with high confidentiality impact and required user interaction.
Likely exposure
Exposure is limited to applications using LangSmith SDK Python versions before 0.8.0 or JS/TS versions before 0.6.0 and calling public prompt pull APIs such as pull_prompt, pullPrompt, or commit variants.
Exploitation context
The provided sources do not report active exploitation, and the CVE is not marked KEV. Exploitation requires a user or system to pull a public prompt controlled by another party, after which the vulnerable SDK deserializes the manifest without an adequate trust boundary distinction.
Researcher notes
Evidence is strongest for affected versions, affected APIs, trust-boundary failure, and fixed releases. The source bundle does not establish active exploitation, complete exploit mechanics, or downstream product-specific impact beyond deserialized LangChain objects and model configuration influencing runtime behavior.
Mitigation direction
- Upgrade LangSmith SDK Python to 0.8.0 or later.
- Upgrade LangSmith SDK JS/TS to 0.6.0 or later.
- Avoid pulling public prompts from untrusted owners until upgraded.
- Review vendor advisory for any additional project-specific guidance.
Validation and detection
- Inventory LangSmith SDK versions in Python and JS/TS dependency manifests.
- Search code for pull_prompt, pull_prompt_commit, pullPrompt, and pullPromptCommit usage.
- Identify whether those calls pull public owner/name prompts.
- Confirm upgraded builds no longer include vulnerable SDK versions.
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-502: Code execution behavior lookup
Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process 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 lookupCVE-2026-45134 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
- 7.1 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/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
1 official scoreWe 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:R/S:U/C:H/I:L/A:N2.84.2GitHub_MVulnerability scoring details
Base CVSS 3.1 score
7.1HighVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/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.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-3644-q5cj-c5c7CVE reference, GitHub_M · x_refsource_CONFIRM
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.
Deserialization of Untrusted Data
Deserialization of Untrusted Data represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.