RCE in Langchain
CVE-2023-36281
An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.034 (88.6th percentile), scored .
Low probability of exploitation in the next 30 days, but still tracked. 89th percentile — 88.6% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.034 · newest: 0.034 · change: 0.000
Affected products
- Langchain — versions 0.0.171
Weakness classification (CWE)
Public proof-of-concept exploits
References
- github.com/hwchase17/langchain/issues/4394 (Exploit, Issue Tracking, Vendor Advisory)
- aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55 (Exploit, Third Party Advisory)
- github.com/langchain-ai/langchain/releases/tag/v0.0.312
Frequently asked questions
- What is CVE-2023-36281?
- CVE-2023-36281 is a critical-severity vulnerability in Langchain, classified under Code Injection. CVSS score: 9.8/10. Published 2023-08-22.
- How severe is CVE-2023-36281?
- Critical severity. CVSS v3 base score is 9.8 out of 10.
- Is CVE-2023-36281 known to be exploited?
- 4 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.