CVE-2025-8709VulnerabilityPublished 26 Oct 2025Updated 28 Oct 2025

CVE-2025-8709: langchain-ai/langchain · Improper Neutralization of Special Elements used in an SQL Command

Affects langchain-ai/langchainSource CVE Database V5

Not known to be exploited · CVSS 7.3 High.

Data as of 25 Oct 2026, 19:02 UTC

CVSS 3.0 base score

7.3High

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

EPSS: 0.2% chance of exploitation in 30 days – higher than 12% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N

Attack Vector: Local
Attack Complexity: Low
Privileges Required: Low
User Interaction: None
Scope: Changed
Confidentiality: High
Integrity: Low
Availability: None

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

Attack Vector: Local: The vulnerable component is not bound to the network stack and the attacker’s path is via read/write/execute capabilities. Either: the attacker exploits the vulnerability by accessing the target system locally (e.g., keyboard, console), or remotely (e.g., SSH); or the attacker relies on User Interaction by another person to perform actions required to exploit the vulnerability (e.g., tricking a legitimate user into opening a malicious document).
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: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
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: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on 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 26 Oct 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
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), the Metasploit, Exploit-DB and nuclei-templates index as of 2026-10-25.

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.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC 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

Affected software

Product	Affected	Fixed in
GitHublangchain-ai/langchain`pkg:github/langchain-ai/langchain`Other threats	Affected =2.0.10	Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

1. Immediately audit all deployments of langchain-ai/langchain, specifically checking for usage of LangGraph's SQLite store version 2.0.10 or earlier. 2. Apply vendor patches or updates as soon as they become available; monitor official repositories and security advisories for fixes. 3. Until patches are available, implement strict input validation and sanitization on all filter operator inputs to prevent injection payloads. 4. Refactor the code to use parameterized queries or prepared statements instead of string concatenation for SQL commands. 5. Restrict access to systems running vulnerable versions to trusted personnel only and monitor for suspicious activity or unauthorized access attempts. 6. Employ database activity monitoring tools to detect anomalous SQL queries indicative of injection attempts. 7. Review and tighten privilege management to minimize the number of users with local access rights. 8. Conduct security awareness training to highlight risks of local privilege misuse. 9. Consider isolating or sandboxing the LangGraph SQLite store to limit potential data exposure. 10. Maintain regular backups and have an incident response plan ready in case of exploitation.

Description

A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters.

Impact

For European organizations, the impact of CVE-2025-8709 is substantial, especially for those integrating langchain-ai/langchain in their AI or data processing pipelines. Unauthorized SQL injection can lead to exposure of sensitive corporate data, including credentials and API keys, which could facilitate further compromise or data breaches. This can result in regulatory non-compliance under GDPR due to unauthorized data disclosure, leading to legal and financial penalties. The breach of confidentiality could damage customer trust and corporate reputation. Since the vulnerability requires local privileges, insider threats or compromised accounts pose a significant risk vector. Organizations relying on LangGraph's SQLite store for critical data storage are particularly vulnerable. The lack of availability impact means systems remain operational but compromised, potentially allowing stealthy data exfiltration. The absence of known exploits in the wild provides a window for mitigation but also means attackers could develop exploits rapidly once the vulnerability is public knowledge.

CWE-89Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #2OWASP Top 10 A05:2025: Injection (opens in a new tab)
The product constructs all or part of an SQL command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended SQL command when it is sent to a downstream component. Without sufficient removal or quoting of SQL syntax in user-controllable inputs, the generated SQL query can cause those inputs to be interpreted as SQL instead of ordinary user data.
Architecture and Design · Libraries or Frameworks
Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Architecture and Design · Parameterization
If available, use structured mechanisms that automatically enforce the separation between data and code. These mechanisms may be able to provide the relevant quoting, encoding, and validation automatically, instead of relying on the developer to provide this capability at every point where output is generated.
Architecture and Design · Operation · Environment Hardening
Run your code using the lowest privileges that are required to accomplish the necessary tasks. If possible, create isolated accounts with limited privileges that are only used for a single task. That way, a successful attack will not immediately give the attacker access to the rest of the software or its environment.
OWASP Cheat Sheets
Query Parameterization (opens in a new tab)
Unvalidated Redirects and Forwards (opens in a new tab)
XML Security (opens in a new tab)
XML External Entity Prevention (opens in a new tab)
File Upload (opens in a new tab)
OWASP ASVS 4.0.3
V5.3.4 (opens in a new tab)
V5.3.5 (opens in a new tab)
V1.5.1 (opens in a new tab)
Attack patterns
Command Line Execution through SQL Injection (opens in a new tab)
Object Relational Mapping Injection (opens in a new tab)
SQL Injection through SOAP Parameter Tampering (opens in a new tab)
Expanding Control over the Operating System from the Database (opens in a new tab)
SQL Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

huntr.com/bounties/9793f4b3-76f8-44a4-989f-49a2177ee118 (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 2 Nov 2025, 06:07 UTC

WeaknessesCWE-89

Technical details

References

Community reviews

Related threats