Advisoriesby IbisLangChainGHSA-92j5-3459-qgp4
LangChain vulnerable to arbitrary code execution
Fix: upgrade to 0.0.236 or later
An issue in Harrison Chase langchain before version 0.0.236 allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| langchain PyPI | < 0.0.236 | 0.0.236 |
Details and references
- CVSS 3.1
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-74, CWE-94
- Also known as
- CVE-2023-38896, PYSEC-2023-146
- nvd.nist.gov/vuln/detail/CVE-2023-38896
- github.com/hwchase17/langchain/issues/5872
- github.com/hwchase17/langchain/pull/6003
- github.com/langchain-ai/langchain/commit/8ba9835b925473655914f63822775679e03ea137
- github.com/langchain-ai/langchain/commit/e294ba475a355feb95003ed8f1a2b99942509a9e
- github.com/langchain-ai/langchain
- github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-146.yaml
- twitter.com/llm_sec/status/1668711587287375876
More LangChain advisories
All LangChain
Langchain vulnerable to arbitrary code execution via the evaluate function in the numexpr libraryCVE-2023-39631fixed in 0.0.308langchain vulnerable to arbitrary code executionCVE-2023-36281fixed in 0.0.312LangChain vulnerable to arbitrary code executionCVE-2023-38860fixed in 0.0.247LangChain vulnerable to arbitrary code executionCVE-2023-39659fixed in 0.0.325langchain Code Injection vulnerabilityCVE-2023-36095fixed in 0.0.236langchain vulnerable to arbitrary code executionCVE-2023-36188fixed in 0.0.247