Remote code execution via unsanitized Python eval
Published Sep 1, 2023 · Updated Oct 1, 2024
Code injection in LangChain before 0.0.308 allows remote attackers to execute arbitrary code through crafted LLMMathChain prompts. LLMMathChain passes model-produced expressions to NumExpr evaluate, whose stringToExpression function invokes Python eval without rejecting executable syntax. Exposure requires an application to let untrusted prompt content reach LLMMathChain while using the optional NumExpr dependency; code runs with the application's privileges.
Summary
What happened
Code injection in LangChain before 0.0.308 allows remote attackers to execute arbitrary code through crafted LLMMathChain prompts. LLMMathChain passes model-produced expressions to NumExpr evaluate, whose stringToExpression function invokes Python eval without rejecting executable syntax. Exposure requires an application to let untrusted prompt content reach LLMMathChain while using the optional NumExpr dependency; code runs with the application's privileges.
The record
- CVE
- CVE-2023-39631
- Published
- Sep 1, 2023
- Updated
- Oct 1, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 1, 2023CVE publishedPublication date reported by the CVE source.
- Oct 1, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- NumExpr evaluate code-execution proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo