CVE-2025-68664VulnerabilityPublished 23 Dec 2025Updated 27 Oct 2026

Langchain core: LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

Affects langchain-coreSource GCVE Database

Authoritative record:CVE-2025-68664· Critical 9.3

Public exploit available (Exploit-DB) · CVSS 9.3 Critical : upgrade to 1.2.5 as a priority.

Data as of 27 Oct 2026, 18:30 UTC

CVSS 3.1 base score

9.3Critical

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

Patch: Available – fixed in 1.2.5, 0.3.81

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
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: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
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

t = 0 is the CVE’s publication on cve.org

Disclosed: evidence found.
CVE published 23 Dec 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: evidence found.
1 Exploit-DB entry, 127 days after disclosure
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

CVE ID reserved
by GitHub, Inc.
22 Dec 202523:28 UTC, 23 hours before disclosure
CVE published
on cve.org
23 Dec 202522:47 UTC, t = 0
In Threat Radar
record ingested
23 Dec 202522:56 UTC, 9 minutes after disclosure
First Exploit-DB entry (opens in a new tab)
LangChain Core 1.2.4 - SSTI/RCE
29 Apr 2026, 127 days after disclosure

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 26 Oct 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.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, 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-core to 1.2.5; langchain-core to 0.3.81.

Affected software

Product	Affected	Fixed in
PyPIlangchain-core	Affected >=1.0.0 <1.2.5	Fixed in 1.2.5
PyPIlangchain-core	Affected <0.3.81	Fixed in 0.3.81

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

AI-suggested

A patch is available in LangChain core versions 1.2.5 and 0.3.81 that fixes the escaping bug in dumps() and dumpd() and hardens deserialization defaults by restricting allowed objects, disabling secrets_from_env by default, and blocking Jinja2 templates. Users should upgrade to these fixed versions. If upgrading is not immediately possible, avoid deserializing untrusted data and disable secrets_from_env to prevent secret extraction. Review usage of vulnerable serialization APIs and avoid passing user-controlled data containing 'lc' keys to dumps() or dumpd().

Description

A serialization injection vulnerability in LangChain core affects the dumps() and dumpd() functions, which fail to escape user-controlled dictionaries containing 'lc' keys. This allows maliciously crafted serialized data to be deserialized as legitimate LangChain objects, enabling secret extraction from environment variables and instantiation of classes within trusted namespaces with attacker-controlled parameters. The vulnerability impacts applications that deserialize untrusted data or use certain LangChain features relying on vulnerable serialization. A patch is available in versions 1.2.5 and 0.3.81 that fixes the escaping bug and hardens deserialization defaults.

Impact

Attackers able to control serialized input can extract environment variable secrets if secrets_from_env is enabled (the old default) and instantiate classes within trusted namespaces with attacker-controlled parameters, potentially causing side effects such as network calls or file operations. This compromises confidentiality by leaking secrets and may lead to unintended behavior or privilege escalation via class instantiation. The vulnerability affects applications that trust their own serialization output or deserialize untrusted data containing 'lc' keys, including those using vulnerable LangChain features like astream_events v1, Runnable.astream_log(), RunnableWithMessageHistory, InMemoryVectorStore.load(), and others.

CWE-502Deserialization of Untrusted Data (opens in a new tab)
Base weaknessLikelihood of exploit: MediumCWE Top 25 (2025): #15OWASP Top 10 A08:2025: Software or Data Integrity Failures (opens in a new tab)
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
Architecture and Design · Implementation
If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
Implementation
When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
Implementation
Explicitly define a final object() to prevent deserialization.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
XML Security (opens in a new tab)
XML External Entity Prevention (opens in a new tab)
Software Supply Chain Security (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.2 (opens in a new tab)
V5.5.3 (opens in a new tab)
V5.5.1 (opens in a new tab)
Attack patterns
Object Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

Timeline

What to do

Affected software

Description

AI analysisMachine-generated, updated 27 Oct 2026, 18:30 UTC

Public exploits and detection1 Exploit-DB entry

WeaknessesCWE-502

Technical details

References

Community reviews

Related threats