CVE-2024-28088 json
LangChain directory traversal vulnerability
published 2024-03-03 2 y ago modified 2026-06-17 4 mo ago also GHSA-h59x-p739-982c , PYSEC-2024-43 , PYSEC-2024-45 , EUVD-2024-0085
- cvss
- 8.1
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.7%
- EPSS 1.7% chance of exploitation in 30 days, percentile 77%
- public exploits
- 0
- none known
Summary
LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome can be disclosure of an API key for a large language model online service, or remote code execution. (A patch is available as of release 0.1.29 of langchain-core.)
Patch / fix
- pypi langchain 0.0.339, 0.1.11
- pypi langchain-core 0.1.11, 0.1.30
- langchain langchain 0.1.12
- github.com/langchain-ai/langchain@e1924b3 commit
- github.com/langchain-ai/langchain#18600 pull request
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 2 y ago
Exploit prediction
1.73% chance of exploitation in the next 30 days, higher than 77% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/langchain-ai/langchain/pull/18600 referenced PoC, tagged "exploit" by a source, unverified
- github.com https://github.com/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CISA ADP | 3.1 | 8.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N |
| NVD | 3.1 | 8.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N |
| CNA | 3.1 | 8.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langchain | <0.0.339 <0.1.11 |
0.0.339 0.1.11 |
| pypi | langchain-core | <0.1.30 <0.1.11 |
0.1.30 0.1.11 |
Affected products
- langchain langchain
Classification
References
-
github.com
/langchain-ai/langchain/pull/18600
web, exploit, issue-tracking, patch
-
github.com
/langchain-ai/langchain/commit/e1924b3e93d513ca950c72f8e80e1c133749fba5
web
-
github.com
/PinkDraconian/PoC-Langchain-RCE/blob/main/README.md
web, exploit, third-party-advisory
-
github.com
/langchain-ai/langchain/blob/f96dd57501131840b713ed7c2e86cbf1ddc2761f/libs/core/langchain_core/utils/loading.p
web, product, third-party-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2024-28088
advisory
-
github.com
/langchain-ai/langchain
package
-
github.com
/pypa/advisory-database/tree/main/vulns/langchain-core/PYSEC-2024-45.yaml
web
-
github.com
/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2024-43.yaml
web
-
github.com
/advisories/GHSA-h59x-p739-982c
advisory
Sources
- CVE List CVE-2024-28088
- GitHub Advisory GHSA-h59x-p739-982c
- NVD CVE-2024-28088
- OSV PYSEC-2024-45
- OSV PYSEC-2024-43
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.