CVE-2023-38860 json
LangChain vulnerable to arbitrary code execution
published 2023-08-15 3 y ago modified 2026-06-17 4 mo ago also GHSA-fj32-q626-pjjc , PYSEC-2023-145 , EUVD-2023-0113
- cvss
- 9.8
- version 3.1, NVD
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.4%
- EPSS 1.4% chance of exploitation in 30 days, percentile 72%
- public exploits
- 0
- none known
Summary
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
Patch / fix
- pypi langchain 0.0.247
- github.com/langchain-ai/langchain@d353d66 commit
- github.com/langchain-ai/langchain@fab2445 commit
- github.com/langchain-ai/langchain#8092 pull request
- github.com/langchain-ai/langchain#8425 pull request
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 2 y ago
Exploit prediction
1.41% chance of exploitation in the next 30 days, higher than 72% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/hwchase17/langchain/issues/7641 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| NVD | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langchain | <0.0.247 |
0.0.247 |
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
-
github.com
/langchain-ai/langchain/pull/8092
web
-
github.com
/langchain-ai/langchain/pull/8425
web
-
github.com
/langchain-ai/langchain/commit/d353d668e4b0514122a443cef91de7f76fea4245
web
-
github.com
/langchain-ai/langchain/commit/fab24457bcf8ede882abd11419769c92bc4e7751
web
-
github.com
/hwchase17/langchain/issues/7641
web, exploit, issue-tracking
-
nvd.nist.gov
/vuln/detail/CVE-2023-38860
advisory
-
github.com
/langchain-ai/langchain/issues/7641
web, evidence, report
-
github.com
/hwchase17/langchain
package
-
github.com
/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-145.yaml
web
-
github.com
/advisories/GHSA-fj32-q626-pjjc
advisory
Sources
- CVE List CVE-2023-38860
- GitHub Advisory GHSA-fj32-q626-pjjc
- NVD CVE-2023-38860
- OSV PYSEC-2023-145
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.