Arbitrary code execution via executable Python prompt files
Published Jun 20, 2023 · Updated Dec 9, 2024
Arbitrary code execution in LangChain before 0.0.247 allows context-dependent attackers to run Python code through a crafted prompt file. The load_prompt path uses Python import machinery to execute a supplied .py file while retrieving its PROMPT object, so top-level statements run unchecked. An application or user must direct load_prompt to the crafted local file or URL; execution inherits the LangChain process privileges.
Summary
What happened
Arbitrary code execution in LangChain before 0.0.247 allows context-dependent attackers to run Python code through a crafted prompt file. The load_prompt path uses Python import machinery to execute a supplied .py file while retrieving its PROMPT object, so top-level statements run unchecked. An application or user must direct load_prompt to the crafted local file or URL; execution inherits the LangChain process privileges.
The record
- CVE
- CVE-2023-34541
- Published
- Jun 20, 2023
- Updated
- Dec 9, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- T1203
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 20, 2023CVE publishedPublication date reported by the CVE source.
- Dec 9, 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
- Executable Python prompt-file 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