LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.
CVE-2025-68664
“▲” beside the score: it is higher than NVD's CVSS score.
Score 9.3 from GitHub Security Advisory (severity: CRITICAL) published 2025-12-23. NVD baseline CVSS 8.2; sources differ by 1.1.
Also known asEUVD-2025-204849 (ENISA EUVD) · GHSA-c67j-w6g6-q2cm (GitHub Security Advisories)Source: ENISA EUVD
- Public exploit or proof-of-concept code is available
A fix is available — apply it.
- CVSS v3
- 8.2
- EG Score
- 9.3CRITICALmedium confidence
- EG Risk
- 74EG Risk 74/100
EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.
How it’s computed (value × EchelonGraph’s weight)Severity93% × 45%Impact severity (EG Severity): CVSS 9.3 of 10. Never the KEV-floored or EPSS-lifted EG Score.Exploitation43% × 40%FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.Automatability100% × 15%CISA's SSVC Automatable value: yes (Vulnrichment).SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.Action: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high. - EPSS PROB
- 43%
- EPSS %ILE
- 98th
- KEV
- Not listed
What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)
The EG score (9.3): severity, escalated by confirmed exploitation. This CVE's 9.3 is its impact severity (EG Severity), not escalated.
- EG Severity
- 9.3 CRITICALCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
- EG Likelihood
- 43% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-02). FIRST's exploitation probability, not an EchelonGraph model.
- Confirmed exploitation
- None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
- EG Priority
- SSVC Track at medium mission impactTrack at low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; 60 days if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.
SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Attend at high (mission-essential systems).
A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table
BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; 60 days if it is not.
The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it
Published
December 23, 2025
Last Modified
October 19, 2026
Advisory Details (7)
Auto-updated Sep 15, 2026LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs · Advisory · langchain-ai/langchain · GitHub
https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cmlangchain-core==1.2.5
Patch available: langchain-ai/langchain langchain-core==1.2.5
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5langchain-core==0.3.81
Patch available: langchain-ai/langchain langchain-core==0.3.81
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81fix(core): serialization patch
Fix merged in langchain-ai/langchain PR #34458 on 2025-12-23 — awaiting tagged release
https://github.com/langchain-ai/langchain/pull/34458fix(core): serialization patch
Fix merged in langchain-ai/langchain PR #34455 on 2025-12-22 — awaiting tagged release
https://github.com/langchain-ai/langchain/pull/34455commit d9ec4c5cc789 (langchain-ai/langchain)
Fix landed in langchain-ai/langchain commit d9ec4c5cc789 — awaiting tagged release
https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6commit 5ec0fa69de31 (langchain-ai/langchain)
Fix landed in langchain-ai/langchain commit 5ec0fa69de31 — awaiting tagged release
https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8Vendor Advisories for CVE-2025-68664(5)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
- RHSA-2026:1610Red Hat Product SecurityCritical
Red Hat Security Advisory: Red Hat OpenShift Lightspeed 1.0.9 security update
- RHSA-2026:0409Red Hat Product SecurityCritical
Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.5 Container Release Update
- RHSA-2026:0408Red Hat Product SecurityCritical
Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.6 Container Release Update
- RHSA-2026:0406Red Hat Product SecurityCritical
Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.4 Container Release Update
- GHSA-c67j-w6g6-q2cmGitHub Security AdvisoriesCritical
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
Patch Availability(6)
| Vendor / Ecosystem | Fix (by version range) / Patch | Released | Source |
|---|---|---|---|
| redhat | openshift-lightspeed/lightspeed-service-api-rhel9:1769058587 | 2026-01-30 | redhat |
| redhat | ansible-automation-platform-24/lightspeed-rhel8:1767342459 | 2026-01-08 | redhat |
| redhat | ansible-automation-platform-25/lightspeed-rhel8:1767216121 | 2026-01-08 | redhat |
| redhat | ansible-automation-platform-26/lightspeed-rhel9:1767625654 | 2026-01-08 | redhat |
| pip | langchain-core @ 0.3.81 (fixes < 0.3.81) | — | ghsa |
| pip | langchain-core @ 1.2.5 (fixes >= 1.0.0, < 1.2.5) | — | ghsa |
Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.
Affected Packages
(1 across 1 ecosystem)
PyPI(1)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| langchain-core | 0.0.1 ... 1.2.4 (229 versions) |
| — |
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 13× in last 7d / 57× in last 30d)
Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.
Showing the most recent 99 of 202 refreshes on record for this CVE.
A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. 1 repeat row among the latest 100 is merged into the row it repeats. The 103 oldest rows on record are not shown and were not checked, so the counts can still include repeats.
- 2026-11-03 16:45 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-11-03 08:32 UTCEG score recompute
- 2026-11-03 08:32 UTCVendor advisory
- 2026-11-03 08:32 UTCGHSA enrichmentGHSA-c67j-w6g6-q2cm · GitHub severity CRITICAL · GitHub CVSS 9.3
- 2026-11-02 08:16 UTCEG score recompute
- 2026-11-02 08:16 UTCVendor advisory
- 2026-11-02 08:16 UTCGHSA enrichmentGHSA-c67j-w6g6-q2cm · GitHub severity CRITICAL · GitHub CVSS 9.3
- 2026-11-01 08:01 UTCGHSA enrichmentGHSA-c67j-w6g6-q2cm · GitHub severity CRITICAL · GitHub CVSS 9.3
- 2026-11-01 08:01 UTCEG score recompute▲ 0.90
- 2026-10-31 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-30 16:33 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-29 16:32 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-28 16:30 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-27 17:55 UTCEG score recompute
- 2026-10-27 17:55 UTCVendor advisory
- 2026-10-27 16:30 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-25 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-25 16:05 UTCEG score recompute
- 2026-10-24 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-23 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-22 16:33 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-21 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-20 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-19 22:28 UTCEG score recompute▼ 0.90
- 2026-10-19 22:28 UTCVendor advisory
Show 74 moreShow fewer
- 2026-10-19 22:25 UTCNVD updateCVSS v3 → 8.2 · severity → HIGH
- 2026-10-19 22:01 UTCEG score recompute
- 2026-10-19 22:01 UTCVendor advisory
- 2026-10-19 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-18 20:52 UTCEG score recompute
- 2026-10-18 20:52 UTCVendor advisory
- 2026-10-18 05:17 UTCEG score recompute
- 2026-10-17 20:21 UTCEG score recompute
- 2026-10-17 20:21 UTCVendor advisory
- 2026-10-17 16:33 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-16 20:05 UTCEG score recompute
- 2026-10-16 20:05 UTCVendor advisory
- 2026-10-16 16:39 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-15 17:40 UTCEG score recompute
- 2026-10-15 17:40 UTCVendor advisory
- 2026-10-15 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-14 16:31 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-14 11:33 UTCEG score recompute
- 2026-10-14 11:33 UTCVendor advisory
- 2026-10-13 16:33 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-13 10:36 UTCVendor advisory
- 2026-10-12 16:47 UTCEG score recompute
- 2026-10-12 10:11 UTCVendor advisory
- 2026-10-11 20:21 UTCEG score recompute
- 2026-10-11 18:34 UTCEG score recompute
- 2026-10-11 15:08 UTCEG score recompute
- 2026-10-11 13:47 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-10 19:59 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-09 20:06 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-08 17:11 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-07 23:47 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-06 15:17 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-03 14:25 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-10-03 13:09 UTCOSV refresh
- 2026-10-01 19:49 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-30 15:02 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-29 15:20 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-26 15:58 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-24 14:02 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-23 13:47 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-18 19:27 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-17 19:30 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-16 14:07 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-16 05:14 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-15 03:10 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-14 05:50 UTCOSV refresh
- 2026-09-12 15:00 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-11 09:36 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-10 09:34 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-06 13:47 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-04 05:06 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-02 14:11 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-09-01 13:53 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-30 01:21 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-28 21:40 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-27 14:24 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-26 14:45 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-26 07:13 UTCOSV refresh
- 2026-08-25 13:48 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-24 14:16 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-21 23:48 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-20 22:55 UTCEPSS rescoreEPSS 43% · 98th percentile
- 2026-08-19 17:03 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-18 13:48 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-17 13:46 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-16 14:55 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-16 02:14 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-15 01:30 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-13 22:00 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-12 13:50 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-11 13:42 UTCEPSS rescoreEPSS 42% · 98th percentile
- 2026-08-09 22:58 UTCEG score recompute
- 2026-08-09 22:58 UTCVendor advisory
- 2026-08-08 16:36 UTCEPSS rescoreEPSS 41% · 98th percentile
Publicly available exploits
(2 references)Public exploit code is referenced for this CVE (1 Exploit-DB entry, 1 GitHub PoC). Defenders should treat patch urgency accordingly.
- Exploit-DBEDB-52514Published Apr 29, 2026
LangChain Core 1.2.4 - SSTI/RCE
Open source ↗ - GitHub PoCAk-cybe/CVE-2025-68664-LangGrinch-PoCPublished Dec 27, 2025
A testing framework to identify and demonstrate deserialization vulnerabilities in LangChain Core (<0.3.81). Educational use only
Open source ↗
Related CVEs(same product + same vendor + same CWE)
Same product
8 shownPyPI:langchain-core
Frequently asked(5)
What is CVE-2025-68664?
When was the CVE record for CVE-2025-68664 published?
Is CVE-2025-68664 actively exploited?
What is the CVSS score of CVE-2025-68664?
How do I remediate CVE-2025-68664?
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2025-68664
Is Your Infrastructure Affected by CVE-2025-68664?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.