VulnerabilityPublished 4 Aug 2026

CVE-2026-48121: langchain-ai langgraphjs · Improper Neutralization of Special Elements in Data Query Logic

Affects langchain-ai langgraphjsSource CVE Database V5

Compare

Not known to be exploited · CVSS 6.7 Medium : upgrade to 1.3.1 when convenient.

Data as of 2 Nov 2026, 22:58 UTC

CVSS 3.1 base score

6.7Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.3% chance of exploitation in 30 days – higher than 29% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 1.3.1

CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N

Attack Vector: Adjacent
Attack Complexity: Low
Privileges Required: Low
User Interaction: Required
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Adjacent: The vulnerable component is bound to the network stack, but the attack is limited at the protocol level to a logically adjacent topology. This can mean an attack must be launched from the same shared physical (e.g., Bluetooth or IEEE 802.11) or logical (e.g., local IP subnet) network, or from within a secure or otherwise limited administrative domain (e.g., MPLS, secure VPN to an administrative network zone).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: Required: Successful exploitation of this vulnerability requires a user to take some action before the vulnerability can be exploited.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 4 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
Public exploit code: GitHub proofs of concept
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), GitHub proofs of concept, the Metasploit, Exploit-DB and nuclei-templates index as of 2 Nov 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade langchain-ai langgraphjs to 1.3.1.

Affected software

Product	Affected	Fixed in
langchain-ailanggraphjs	Affected <1.3.1	Fixed in 1.3.1

AI-suggested

Upgrade to langgraphjs version 1.3.1 or later, where this issue is fixed. Until then, ensure that all checkpoint identifier inputs are strictly validated and coerced to strings before being passed to MongoDB queries. Reject or sanitize any non-string input to prevent injection of MongoDB operators. Applications that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected and require no further action.

Description

CVE-2026-48121 is a NoSQL injection vulnerability in langchain-ai's langgraphjs library versions 1.3.0 and below. It arises because checkpoint identifiers used in MongoDB queries are not type-enforced, allowing attackers to inject MongoDB operators to bypass tenant isolation and access unauthorized checkpoint data. The issue is fixed in version 1.3.1.

Impact

Successful exploitation allows an attacker with limited privileges to bypass tenant isolation and access checkpoint data belonging to other tenants, including pending writes. This can lead to unauthorized disclosure of sensitive data. The vulnerability does not impact availability but has high confidentiality and integrity impact. It requires attacker control over input to config.configurable and some privileges to trigger the injection.

Summary

The vulnerability exists in the @langchain/langgraph-checkpoint-mongodb package's CheckpointSaver implementation, which uses MongoDB for storage. In versions 1.3.0 and earlier, checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed directly into MongoDB find() queries without enforcing that they are strings. An attacker supplying an object payload containing MongoDB operators like $gt or $ne can manipulate the query logic, bypassing thread scoping and leaking checkpoint data across tenants. This affects applications that accept untrusted input for these identifiers without coercion or schema validation. Applications that enforce string-only identifiers with schema validation are not vulnerable. The vulnerability is fixed in version 1.3.1.

CWE-943Improper Neutralization of Special Elements in Data Query Logic (opens in a new tab)
Class weakness
The product generates a query intended to access or manipulate data in a data store such as a database, but it does not neutralize or incorrectly neutralizes special elements that can modify the intended logic of the query.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.1 (opens in a new tab)
Attack patterns
NoSQL Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 11 Aug 2026, 18:07 UTC

Public exploits and detectionGitHub proofs of concept

WeaknessesCWE-943

Technical details

References

Community reviews

Related threats