Vulnerability Details : CVE-2023-32786
In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks.
Vulnerability category: Server-side request forgery (SSRF)
Products affected by CVE-2023-32786
- cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*
Exploit prediction scoring system (EPSS) score for CVE-2023-32786
0.09%
Probability of exploitation activity in the next 30 days
EPSS Score History
~ 41 %
Percentile, the proportion of vulnerabilities that are scored at or less
CVSS scores for CVE-2023-32786
| Base Score | Base Severity | CVSS Vector | Exploitability Score | Impact Score | Score Source | First Seen |
|---|---|---|---|---|---|---|
|
7.5
|
HIGH | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
3.9
|
3.6
|
NIST |
CWE ids for CVE-2023-32786
-
The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.Assigned by: nvd@nist.gov (Primary)
References for CVE-2023-32786
-
https://gist.github.com/rharang/d265f46fc3161b31ac2e81db44d662e1
Markdown export of a Jupyter notebook demonstrating the abuse of LangChain's APIChain module to access arbitrary URLs ยท GitHubThird Party Advisory
Jump to