CVE-2026-45134 (GCVE-0-2026-45134)
Vulnerability from cvelistv5 – Published: 2026-05-27 19:35 – Updated: 2026-06-02 18:13- CWE-502 - Deserialization of Untrusted Data
| URL | Tags |
|---|---|
| https://github.com/langchain-ai/langsmith-sdk/sec… | x_refsource_CONFIRM |
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| langchain-ai | langsmith-sdk |
Affected:
< 0.8.0
Affected: < 0.6.0 |
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-45134",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-02T18:13:39.078019Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-02T18:13:59.496Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langsmith-sdk",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.8.0"
},
{
"status": "affected",
"version": "\u003c 0.6.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangSmith Client SDKs provide SDK\u0027s for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK\u0027s 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\u0027s own organization. This vulnerability is fixed in LangSmith SDK Python 0.8.0 and JS/TS 0.6.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-05-27T19:35:32.662Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-3644-q5cj-c5c7",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-3644-q5cj-c5c7"
}
],
"source": {
"advisory": "GHSA-3644-q5cj-c5c7",
"discovery": "UNKNOWN"
},
"title": "LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-45134",
"datePublished": "2026-05-27T19:35:32.662Z",
"dateReserved": "2026-05-08T20:08:17.209Z",
"dateUpdated": "2026-06-02T18:13:59.496Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-45134",
"date": "2026-11-21",
"epss": "0.00199",
"percentile": "0.09753"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "langsmith-sdk",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.8.0"
},
{
"status": "affected",
"version": "\u003c 0.6.0"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "LangSmith Client SDKs provide SDK\u0027s for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK\u0027s 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\u0027s own organization. This vulnerability is fixed in LangSmith SDK Python 0.8.0 and JS/TS 0.6.0."
},
{
"lang": "es",
"value": "Los SDKs de cliente de LangSmith proporcionan SDKs para interactuar con la plataforma LangSmith. Antes de LangSmith SDK Python 0.8.0 y JS/TS 0.6.0, los m\u00e9todos de extracci\u00f3n de prompts del SDK de LangSmith (pull_prompt / pull_prompt_commit en Python, pullPrompt / pullPromptCommit en JS/TS) recuperan y deserializan manifiestos de prompts del LangSmith Hub. Estos manifiestos pueden contener objetos LangChain serializados y configuraci\u00f3n de modelo que afectan el comportamiento en tiempo de ejecuci\u00f3n. Al extraer un prompt p\u00fablico por identificador de propietario/nombre, el contenido del manifiesto es controlado por una parte externa, pero las versiones anteriores del SDK no distingu\u00edan esto de extraer un prompt dentro de la propia organizaci\u00f3n del llamador. Esta vulnerabilidad est\u00e1 corregida en LangSmith SDK Python 0.8.0 y JS/TS 0.6.0."
}
],
"id": "CVE-2026-45134",
"lastModified": "2026-10-26T11:10:00.157",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 4.2,
"source": "security-advisories@github.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-45134",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-02T18:13:39.078019Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-05-27T20:16:38.697",
"references": [
{
"source": "security-advisories@github.com",
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-3644-q5cj-c5c7"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Awaiting Analysis",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-502"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"aggregate_severity": "Moderate",
"current_release_date": "2026-10-15T11:53:21+00:00",
"cve": "CVE-2026-45134",
"id": "CVE-2026-45134",
"initial_release_date": "2026-05-27T19:35:32.662000+00:00",
"product_status:known_affected": "8",
"product_status:known_not_affected": "3",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "langsmith-sdk-python: langsmith-sdk-js: LangSmith Client SDKs: Information disclosure via untrusted prompt deserialization",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-45134.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-45134",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-02T18:13:39.078019Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-02T18:13:43.693Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langsmith-sdk",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.8.0"
},
{
"status": "affected",
"version": "\u003c 0.6.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangSmith Client SDKs provide SDK\u0027s for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK\u0027s 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\u0027s own organization. This vulnerability is fixed in LangSmith SDK Python 0.8.0 and JS/TS 0.6.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-05-27T19:35:32.662Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-3644-q5cj-c5c7",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-3644-q5cj-c5c7"
}
],
"source": {
"advisory": "GHSA-3644-q5cj-c5c7",
"discovery": "UNKNOWN"
},
"title": "LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-45134",
"datePublished": "2026-05-27T19:35:32.662Z",
"dateReserved": "2026-05-08T20:08:17.209Z",
"dateUpdated": "2026-06-02T18:13:59.496Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.