CVE-2023-36095 json
langchain Code Injection vulnerability
published 2023-08-05 3 y ago modified 2026-07-09 4 mo ago also GHSA-gwqq-6vq7-5j86 , PYSEC-2023-138 , EUVD-2023-0112
- cvss
- 9.8
- version 3.1, NVD
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.2%
- EPSS 1.2% chance of exploitation in 30 days, percentile 67%
- public exploits
- 0
- none known
Summary
An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include from_math_prompt and from_colored_object_prompt.
Patch / fix
- pypi langchain 0.0.236
- github.com/langchain-ai/langchain@8ba9835 commit
- github.com/langchain-ai/langchain@e294ba4 commit
- github.com/langchain-ai/langchain#6003 pull request
- github.com/langchain-ai/langchain#7870 pull request
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 2 y ago
Exploit prediction
1.17% chance of exploitation in the next 30 days, higher than 67% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/langchain-ai/langchain/issues/5872 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 | <0.0.236 |
0.0.236 |
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
-
github.com
/langchain-ai/langchain/pull/6003
web
-
github.com
/langchain-ai/langchain/pull/7870
web
-
github.com
/langchain-ai/langchain/commit/8ba9835b925473655914f63822775679e03ea137
web
-
github.com
/langchain-ai/langchain/commit/e294ba475a355feb95003ed8f1a2b99942509a9e
web
-
github.com
/langchain-ai/langchain/issues/5872
web, exploit, issue-tracking, vendor-advisory, evidence, report, advisory
-
github.com
/hwchase17/langchain
web, product
-
nvd.nist.gov
/vuln/detail/CVE-2023-36095
advisory
-
github.com
/langchain-ai/langchain
package
-
github.com
/langchain-ai/langchain/commits/v0.0.236?after=4d8b48bdb3f17c764c5c2e3c7140071603869e74+34&branch=v0.0.236&qua
web
-
github.com
/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-138.yaml
web
-
langchain.com
web
-
github.com
/advisories/GHSA-gwqq-6vq7-5j86
advisory
Sources
- CVE List CVE-2023-36095
- GitHub Advisory GHSA-gwqq-6vq7-5j86
- NVD CVE-2023-36095
- OSV PYSEC-2023-138
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.