Remote code execution via unchecked agent prompt
Published Aug 15, 2023 · Updated Oct 8, 2024
Code injection in LangChain before 0.0.325 allows remote attackers to execute arbitrary Python code through a crafted agent prompt. PythonAstREPLTool._run passes model-selected prompt content to Python execution without sanitizing or restricting dangerous operations. Exposure requires an application that accepts attacker-controlled prompts and equips its agent with the Python REPL tool; successful exploitation runs commands with the host process's permissions.
Summary
What happened
Code injection in LangChain before 0.0.325 allows remote attackers to execute arbitrary Python code through a crafted agent prompt. PythonAstREPLTool._run passes model-selected prompt content to Python execution without sanitizing or restricting dangerous operations. Exposure requires an application that accepts attacker-controlled prompts and equips its agent with the Python REPL tool; successful exploitation runs commands with the host process's permissions.
The record
- CVE
- CVE-2023-39659
- Published
- Aug 15, 2023
- Updated
- Oct 8, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-74, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 15, 2023CVE publishedPublication date reported by the CVE source.
- Oct 8, 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.
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
- LangChain prompt-injection reproductionproof 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