LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
langchain-ai · langsmith-sdk
7.1HighCVSS 3.1
Recommended action
Within 7 days
High technical severity; prioritise exposed affected systems while verifying vendor guidance.
Mitigation available
Direct vendor intelligence
Authoritative vendor CSAF and VEX advisories
Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.
1 current
CVE-2026-45134 · CSAF 2.0 · revision 3 · finalRed Hat Product Securitylangsmith-sdk-python: langsmith-sdk-js: LangSmith Client SDKs: Information disclosure via untrusted prompt deserialization
9 known affected
The vendor explicitly identifies these products as affected by this CVE.
openshift-lightspeed/lightspeed-service-api-rhel9 as a component of OpenShift Lightspeed
ansible-automation-platform-24/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2
ansible-automation-platform-25/lightspeed-chatbot-rhel8 as a component of Red Hat Ansible Automation Platform 2
ansible-automation-platform-25/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2
rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
rhelai3/disk-image-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
rhoai/odh-llama-stack-core-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
rhoai/odh-trustyai-nemo-guardrails-server-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
Summary
A flaw was found in the LangSmith Client SDKs. This vulnerability allows an external attacker to control the content of prompt manifests when a user pulls a public prompt from the LangSmith Hub. By exploiting the deserialization of untrusted data, an attacker could achieve high confidentiality impact, potentially leading to the disclosure of sensitive information and affecting the application's runtime behavior.
Remediation
To mitigate this vulnerability, avoid pulling public prompts from the LangSmith Hub using the LangSmith Client SDKs without explicit trust. The SDK provides a `dangerously_pull_public_prompt` flag (Python) or `dangerouslyPullPublicPrompt` (JS/TS) that must be set to `True` to enable pulling public prompts by `owner/name`. Do not enable this flag unless the prompt's contents have been independently reviewed and trusted. Additionally, when pulling prompts, avoid setting `include_model=True` or `secrets_from_env=True` if the prompt source is untrusted, as these options expand the deserialization allowlist and allow reading environment variables.
Optional official sources
National CERT insights ?CERT means Computer Emergency Response Team; CSIRT is the closely related term Computer Security Incident Response Team.
Select the national-authority views to include. The exact source language is shown on each matched advisory. Your choice is remembered on this device and encoded in the shareable URL.
Official European source
ENISA European Vulnerability Database
Official EUVD identifiers, advisory evidence and known-exploited context. Missing fields are not treated as evidence of low risk.
1 current
ENISA EUVD identifier
EUVD-2026-32640
No EUVD known-exploited evidence
ENISA has published the identifier mapping but no EUVD description has been stored yet.
EUVD state
Present in the current official mapping
Known exploitation
Not present in the current ENISA EUVD known-exploited dataset. This is not proof of no exploitation.
ENISA score
Not supplied in the stored EUVD record
Advisory evidence
No linked advisory details stored yet
Recommended actionWithin 7 days
High technical severity; prioritise exposed affected systems while verifying vendor guidance.
Mitigation available
01
What, why and how
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods (pull_prompt / pull_prompt_commit in Python, pullPrompt / pullPromptCommit in JS/TS) fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model configuration that affect runtime behavior. When pulling a public prompt by owner/name identifier, the manifest content is controlled by an external party, but prior versions of the SDK did not distinguish this from pulling a prompt within the caller's own organization. This vulnerability is fixed in LangSmith SDK Python 0.8.0 and JS/TS 0.6.0.
What
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods (pull_prompt / pull_prompt_commit in Python, pullPrompt / pullPromptCommit in JS/TS) fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model configuration that affect runtime behavior. When pulling a public prompt by owner/name identifier, the manifest content is controlled by an external party, but prior versions of the SDK did not distinguish this from pulling a prompt within the caller's own organization. This vulnerability is fixed in LangSmith SDK Python 0.8.0 and JS/TS 0.6.0.
Why
Attacker-influenced serialised data is reconstructed as trusted objects, which can invoke dangerous application behaviour.
How
An attacker operating through a network path may attempt exploitation without authentication after a user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.
What
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods (pull_prompt / pull_prompt_commit in Python, pullPrompt / pullPromptCommit in JS/TS) fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model configuration that affect runtime behavior. When pulling a public prompt by owner/name identifier, the manifest content is controlled by an external party, but prior versions of the SDK did not distinguish this from pulling a prompt within the caller's own organization. This vulnerability is fixed in LangSmith SDK Python 0.8.0 and JS/TS 0.6.0.
Why
Attacker-influenced serialised data is reconstructed as trusted objects, which can invoke dangerous application behaviour.
How
An attacker operating through a network path may attempt exploitation without authentication after a user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.
02
Exploit reality and attack path
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
Observed exploitation ?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No confirmed evidence
No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
Public PoC / exploit material ?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.None recorded
No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.
Likely attack path
a network path → Deserialization of Untrusted Data → cause the confidentiality, integrity or availability impact described by the vendor
Attack surface
Network
Privileges required
None: unauthenticated exploitation is possible
User interaction
Required interaction required
Attack complexity
Low: no specialised conditions are recorded
Security boundary
Unchanged: impact remains within the vulnerable component's security authority
Weakness ?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-502: Deserialization of Untrusted Data. The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
CVSS vector ?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N
Common Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRNonePrivileges required: The attacker does not need an account or existing privileges.UIRequiredUser interaction: Another user must perform an action for exploitation to succeed.SUnchangedScope: The security impact remains within the vulnerable component's authority.CHighConfidentiality impact: A successful attack can cause a major loss.ILowIntegrity impact: A successful attack can cause a limited loss.ANoneAvailability impact: No direct loss is represented by this metric.
Post-exploitation / living off the land
No specific living-off-the-land technique is confirmed in the structured sources. Monitor normal administration tools for activity inconsistent with the affected service's baseline.
NetworkUnauthenticatedCWE-502
A
Official authority intelligence
Only matched European and national findings are included. Language selectors and unavailable sources are omitted.
ENISA EUVD · EUVD-2026-32640Official EUVD mapping
0 linked advisory records.
Official EUVD record ↗Cyber Security Agency of Singapore · English · CSA-SB-20260603Security Bulletin 3 Jun 2026
The Cyber Security Agency of Singapore included this CVE in its official Security Bulletin 3 Jun 2026, published on 3 June 2026. Open the linked bulletin for the product, severity and reference information published in that issue.
Operational remediation based on structured source evidence.
Status ?Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change.
No verified patch reference is present in the current structured sources. Check the vendor advisory before making a change.
Workaround
To mitigate this vulnerability, avoid pulling public prompts from the LangSmith Hub using the LangSmith Client SDKs without explicit trust. The SDK provides a `dangerously_pull_public_prompt` flag (Python) or `dangerouslyPullPublicPrompt` (JS/TS) that must be set to `True` to enable pulling public prompts by `owner/name`. Do not enable this flag unless the prompt's contents have been independently reviewed and trusted. Additionally, when pulling prompts, avoid setting `include_model=True` or `secrets_from_env=True` if the prompt source is untrusted, as these options expand the deserialization allowlist and allow reading environment variables.
04
Evidence and provenance
Published 27 May 2026 · Last source change 2 Jun 2026, 18:13 UTC · CWE-502 · Deserialization of Untrusted Data
CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source ?The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.FIRST · tracked since 2026-08-14
European sourceENISA EUVD · EUVD-2026-32640
Product sourceVendor CSAF · Red Hat Product Security
Remediation sourceVendor CSAF · Red Hat Product Security
CWE sourceCNA
NVD statusNVD awaiting enrichment
Core structured fields are present and their contributing authorities are shown above.
Affected versionsThe structured affected or fixed version information changed.
Before
openshift-lightspeed/lightspeed-service-api-rhel9 as a component of OpenShift Lightspeed; ansible-automation-platform-24/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-chatbot-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-26/lightspeed-rhel9 as a component of Red Hat Ansible Automation Platform 2; rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/disk-image-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhoai/odh-llama-stack-core-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-trustyai-nemo-guardrails-server-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
After
openshift-lightspeed/lightspeed-service-api-rhel9 as a component of OpenShift Lightspeed; ansible-automation-platform-24/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-chatbot-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/disk-image-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhoai/odh-llama-stack-core-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-trustyai-nemo-guardrails-server-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
Affected versionsThe structured affected or fixed version information changed.
Before
openshift-lightspeed/lightspeed-service-api-rhel9 as a component of OpenShift Lightspeed; ansible-automation-platform-24/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-chatbot-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-26/lightspeed-rhel9 as a component of Red Hat Ansible Automation Platform 2; rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/disk-image-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhoai/odh-llama-stack-core-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-mlflow-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-trustyai-nemo-guardrails-server-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
After
openshift-lightspeed/lightspeed-service-api-rhel9 as a component of OpenShift Lightspeed; ansible-automation-platform-24/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-chatbot-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-25/lightspeed-rhel8 as a component of Red Hat Ansible Automation Platform 2; ansible-automation-platform-26/lightspeed-rhel9 as a component of Red Hat Ansible Automation Platform 2; rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/disk-image-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhoai/odh-llama-stack-core-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-trustyai-nemo-guardrails-server-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
Technical terms and abbreviations used in this report
CVE
Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
CVSS
Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
EPSS
Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
CWE
Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
CNA
CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
CISA ADP
Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
NVD
National Vulnerability Database: NIST's enrichment service for CVE records.
CERT / CSIRT
A computer security incident response team that publishes warnings or coordinates incident response.
PoC
Proof of concept: public material that demonstrates or helps reproduce exploitation.
CSAF
Common Security Advisory Framework: a machine-readable format for security advisories.
LoTL
Living off the land: abuse of legitimate tools or system functions during an attack.
CVE-2026-45134: LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning | BlackTree
