CVE-2026-28277 json
LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading
published 2026-03-05 8 mo ago modified 2026-06-17 4 mo ago also EUVD-2026-9860 , GHSA-g48c-2wqr-h844 , PYSEC-2026-83
- cvss
- 6.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 5.5%
- EPSS 5.5% chance of exploitation in 30 days, percentile 92%
- public exploits
- 0
- none known
Summary
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store (for example, after a database compromise or other privileged write access to the persistence layer), they can potentially supply a crafted payload that triggers unsafe object reconstruction when the checkpoint is loaded. No known patch is public.
Patch / fix
- pypi langgraph 1.0.10, 1.0.10rc1
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- total
- Assessed
- 8 mo ago
Exploit prediction
5.49% chance of exploitation in the next 30 days, higher than 92% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 6.8 | CVSS:3.1/AV:A/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 6.8 | CVSS:3.1/AV:A/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H |
| NVD | 3.1 | 7.2 | CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 7.2 | CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langgraph | <1.0.10 <1.0.10rc1 |
1.0.10 1.0.10rc1 |
Affected products
- langchain-ai langgraph
Classification
- Weakness
-
- CWE-502 Deserialization of Untrusted Data
References
-
github.com
/langchain-ai/langgraph/security/advisories/GHSA-g48c-2wqr-h844
web, mitigation, vendor-advisory, advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-28277
advisory
-
github.com
/langchain-ai/langgraph
package
-
github.com
/pypa/advisory-database/tree/main/vulns/langgraph/PYSEC-2026-83.yaml
web
Sources
- CVE List CVE-2026-28277
- GitHub Advisory GHSA-g48c-2wqr-h844
- NVD CVE-2026-28277
- OSV PYSEC-2026-83
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.