LangChain vulnerable to code injection
In LangChain through 0.0.131, the `LLMMathChain` chain allows prompt injection attacks that can execute arbitrary code via the Python `exec()` method.
01
describes (1)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2023-29374US | critical9.8 | — | ||
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method. | ||||
02
references
External citations — patches, advisories, analysis.
- https://github.com/hwchase17/langchain/issues/1026WEB
- https://github.com/hwchase17/langchain/issues/814WEB
- https://github.com/hwchase17/langchain/pull/1119WEB
- https://github.com/langchain-ai/langchainPACKAGE
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-18.yamlWEB
- https://nvd.nist.gov/vuln/detail/CVE-2023-29374ADVISORY
- https://twitter.com/rharang/status/1641899743608463365/photo/1WEB
scry
Advisories like this name the exposed products attackers go after on your perimeter. See what is exposed on your perimeter with a free passive scan.
Free scan