Vulnerability Details : CVE-2023-36095
Potential exploit
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.
Vulnerability category: Execute code
Products affected by CVE-2023-36095
- cpe:2.3:a:langchain:langchain:0.0.194:*:*:*:*:*:*:*
Exploit prediction scoring system (EPSS) score for CVE-2023-36095
1.72%
Probability of exploitation activity in the next 30 days
EPSS Score History
~ 81 %
Percentile, the proportion of vulnerabilities that are scored at or less
CVSS scores for CVE-2023-36095
| Base Score | Base Severity | CVSS Vector | Exploitability Score | Impact Score | Score Source | First Seen |
|---|---|---|---|---|---|---|
|
9.8
|
CRITICAL | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
3.9
|
5.9
|
NIST |
CWE ids for CVE-2023-36095
-
The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.Assigned by: nvd@nist.gov (Primary)
References for CVE-2023-36095
-
http://langchain.com
LangChainProduct
-
https://github.com/langchain-ai/langchain/issues/5872
Prompt injection which leads to arbitrary code execution in `langchain.chains.PALChain` · Issue #5872 · langchain-ai/langchain · GitHubExploit;Issue Tracking;Vendor Advisory
-
https://github.com/hwchase17/langchain
GitHub - langchain-ai/langchain: ⚡ Building applications with LLMs through composability ⚡Product
Jump to