CVE-2023-29374
LangChain vulnerable to code injection
Overview
Description
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
Source: OX vulnerability database
Severity
9.8 · CRITICAL
CVSS 3.1 base score, scored by NVD.
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness: CWE-74
Affected packages · 1
| Ecosystem | Package | Vulnerable | Fixed in |
|---|---|---|---|
| PyPI | langchain | <=0.0.131 | No fix yet |
Open a package to see all its vulnerabilities.
Operating systems
No Linux distribution reports this ID.
References
- github.com https://github.com/hwchase17/langchain/issues/1026
- github.com https://github.com/hwchase17/langchain/issues/814
- github.com https://github.com/hwchase17/langchain/pull/1119
- github.com https://github.com/langchain-ai/langchain
- github.com https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-18.yaml
- nvd.nist.gov https://nvd.nist.gov/vuln/detail/CVE-2023-29374
- twitter.com https://twitter.com/rharang/status/1641899743608463365/photo/1
OX Radar and Response Center
Find threats in your stack.
OX Radar can check high-priority threats, like critical package CVEs, against your context.
Each incident is marked Detected or Not Detected with a remediation plan and proof all tracked in the Response Center.