GHSA-533J-2V4Q-MW5H
Vulnerability from github – Published: 2026-08-20 17:29 – Updated: 2026-08-20 17:29Executive Summary
A NoSQL injection issue exists in the langgraph-checkpoint-mongodb and langgraph-store-mongodb libraries. MongoDBSaver.list() and MongoDBStore.search() methods accept a filter parameter that is incorporated into MongoDB queries without sufficient validation. Because MongoDB query operator keys (those prefixed with $) are not rejected during filter construction, a caller with control of the filter input can embed MongoDB query operators directly into the query.
CVSS Details
CVSS 4.0
| Field | Value |
|---|---|
| CVSS Version | 4.0 |
| Vector String | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N |
| Base Score | 7.1 (High) |
| Metric | Value | Rationale |
|---|---|---|
| Attack Vector (AV) | Network | Triggerable remotely via API |
| Attack Complexity (AC) | Low | No special conditions required |
| Attack Requirements (AT) | None | No prerequisite deployment or execution conditions |
| Privileges Required (PR) | Low | Authenticated caller of the checkpoint/store API |
| User Interaction (UI) | None | No user action required |
| Vulnerable System Confidentiality (VC) | None | No direct impact on the vulnerable component itself |
| Vulnerable System Integrity (VI) | None | Read-only access |
| Vulnerable System Availability (VA) | None | No service disruption |
| Subsequent System Confidentiality (SC) | High | Full access to other tenants' checkpoint data |
| Subsequent System Integrity (SI) | None | No write or modification capability |
| Subsequent System Availability (SA) | None | No service disruption to downstream systems |
CVSS 3.1
| Field | Value |
|---|---|
| CVSS Version | 3.1 |
| Vector String | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N |
| Base Score | 7.7 (High) |
| Metric | Value | Rationale |
|---|---|---|
| Attack Vector | Network | Triggerable remotely via API |
| Attack Complexity | Low | No special conditions required |
| Privileges Required | Low | Authenticated caller of the checkpoint/store API |
| User Interaction | None | No user action required |
| Scope | Changed | Impact crosses tenant boundaries |
| Confidentiality | High | Full access to other tenants' checkpoint data |
| Integrity | None | Read-only access |
| Availability | None | No service disruption |
| --- | ||
| ## Affected Packages | ||
| Package | Distribution | Affected Methods |
| --- | --- | --- |
langgraph-checkpoint-mongodb |
PyPI | MongoDBSaver.list(), MongoDBSaver.alist() |
langgraph-store-mongodb |
PyPI | MongoDBStore.search() |
| --- | ||
| ## Advisory FAQ | ||
| ### How do I know if I am affected? |
You are likely affected if all of the following are true:
1. Your application uses langgraph-checkpoint-mongodb or langgraph-store-mongodb.
2. Your application calls MongoDBSaver.list(), MongoDBSaver.alist(), or
MongoDBStore.search() with a filter argument.
3. Any part of that filter argument is derived from user-controlled input — for example, HTTP
query parameters, request body fields, or agent tool arguments.
4. You operate in a multi-tenant context where the filter is used to enforce per-user or
per-tenant data isolation.
If the filter argument is constructed entirely from trusted, server-side values, the practical risk is
lower, but upgrading is still recommended.
How do I fix the issue?
Upgrade to the version of langgraph-checkpoint-mongodb and langgraph-store-mongodb.
If you cannot upgrade immediately, apply the following mitigation: in your application code,
before passing any user-controlled input to the filter parameter, remove or escape MongoDB
Query metacharacters such as “$”.
Acknowledgements
Thanks to Kenichi Kawaguchi for responsibly disclosing this issue via the GitHub Security Advisory program on the langchain-mongodb repository.
Revisions
| Date | Description |
|---|---|
| 2026-06-05 | Initial advisory published |
{
"affected": [
{
"package": {
"ecosystem": "PyPI",
"name": "langgraph-checkpoint-mongodb"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.3.0"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"package": {
"ecosystem": "PyPI",
"name": "langgraph-store-mongodb"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.4.0"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-55253"
],
"database_specific": {
"cwe_ids": [
"CWE-943"
],
"github_reviewed": true,
"github_reviewed_at": "2026-08-20T17:29:14Z",
"nvd_published_at": null,
"severity": "HIGH"
},
"details": "# Executive Summary\n\nA NoSQL injection issue exists in the langgraph-checkpoint-mongodb and\nlanggraph-store-mongodb libraries. MongoDBSaver.list() and MongoDBStore.search() methods\naccept a filter parameter that is incorporated into MongoDB queries without sufficient validation.\nBecause MongoDB query operator keys (those prefixed with $) are not rejected during filter\nconstruction, a caller with control of the filter input can embed MongoDB query operators\ndirectly into the query.\n\n---\n\n## CVSS Details\n\n### CVSS 4.0\n\n| Field | Value |\n|---|---|\n| **CVSS Version** | 4.0 |\n| **Vector String** | `CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N` |\n| **Base Score** | **7.1 (High)** |\n\n| Metric | Value | Rationale |\n|---|---|---|\n| Attack Vector (AV) | Network | Triggerable remotely via API |\n| Attack Complexity (AC) | Low | No special conditions required |\n| Attack Requirements (AT) | None | No prerequisite deployment or execution conditions |\n| Privileges Required (PR) | Low | Authenticated caller of the checkpoint/store API |\n| User Interaction (UI) | None | No user action required |\n| Vulnerable System Confidentiality (VC) | None | No direct impact on the vulnerable component itself |\n| Vulnerable System Integrity (VI) | None | Read-only access |\n| Vulnerable System Availability (VA) | None | No service disruption |\n| Subsequent System Confidentiality (SC) | High | Full access to other tenants\u0027 checkpoint data |\n| Subsequent System Integrity (SI) | None | No write or modification capability |\n| Subsequent System Availability (SA) | None | No service disruption to downstream systems |\n\n### CVSS 3.1\n\n| Field | Value |\n|---|---|\n| **CVSS Version** | 3.1 |\n| **Vector String** | `CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N` |\n| **Base Score** | **7.7 (High)** |\n\n| Metric | Value | Rationale |\n|---|---|---|\n| Attack Vector | Network | Triggerable remotely via API |\n| Attack Complexity | Low | No special conditions required |\n| Privileges Required | Low | Authenticated caller of the checkpoint/store API |\n| User Interaction | None | No user action required |\n| Scope | Changed | Impact crosses tenant boundaries |\n| Confidentiality | High | Full access to other tenants\u0027 checkpoint data |\n| Integrity | None | Read-only access |\n| Availability | None | No service disruption |\n---\n## Affected Packages\n| Package | Distribution | Affected Methods | Affected Versions |\n|---|---|---|---|\n| `langgraph-checkpoint-mongodb` | PyPI | `MongoDBSaver.list()`, `MongoDBSaver.alist()` | \u003c 0.3.0 |\n| `langgraph-store-mongodb` | PyPI | `MongoDBStore.search()` | \u003c 0.4.0 |\n---\n## Advisory FAQ\n### How do I know if I am affected?\n\nYou are likely affected if **all** of the following are true:\n1. Your application uses `langgraph-checkpoint-mongodb` or `langgraph-store-mongodb`.\n2. Your application calls `MongoDBSaver.list()`, `MongoDBSaver.alist()`, or\n`MongoDBStore.search()` with a `filter` argument.\n3. Any part of that `filter` argument is derived from user-controlled input \u2014 for example, HTTP\nquery parameters, request body fields, or agent tool arguments.\n4. You operate in a multi-tenant context where the `filter` is used to enforce per-user or\nper-tenant data isolation.\n\nIf the `filter` argument is constructed entirely from trusted, server-side values, the practical risk is\nlower, but upgrading is still recommended.\n\n### How do I fix the issue?\n\n**Upgrade** to the version of `langgraph-checkpoint-mongodb` and `langgraph-store-mongodb`.\nIf you cannot upgrade immediately, apply the following mitigation: in your application code,\nbefore passing any user-controlled input to the `filter` parameter, remove or escape MongoDB\nQuery metacharacters such as \u201c$\u201d.\n\n---\n\n## Acknowledgements\nThanks to Kenichi Kawaguchi for responsibly disclosing this issue via the GitHub Security\nAdvisory program on the langchain-mongodb repository.\n\n---\n\n## Revisions\n\n| Date | Description |\n|---|---|\n| 2026-06-05 | Initial advisory published |",
"id": "GHSA-533j-2v4q-mw5h",
"modified": "2026-08-20T17:29:14Z",
"published": "2026-08-20T17:29:14Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langchain-mongodb/security/advisories/GHSA-533j-2v4q-mw5h"
},
{
"type": "PACKAGE",
"url": "https://github.com/langchain-ai/langchain-mongodb"
},
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs%2Flanggraph-checkpoint-mongodb%2Fv0.4.0"
},
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs%2Flanggraph-store-mongodb%2Fv0.3.0"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N",
"type": "CVSS_V3"
}
],
"summary": "LangChain MongoDB has NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure"
}
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.