Remote code execution via unsanitized PALChain prompts
Published Jul 6, 2023 · Updated Nov 19, 2024
Code injection in LangChain before 0.0.247 allows remote attackers to execute arbitrary Python code through a prompt passed to PALChain. PALChain sends model-generated code derived from the prompt directly to Python exec without first preventing imports or arbitrary execution commands. Exposure requires an application to pass attacker-controlled prompts to a PALChain instance; successful exploitation runs code with the application's privileges.
Summary
What happened
Code injection in LangChain before 0.0.247 allows remote attackers to execute arbitrary Python code through a prompt passed to PALChain. PALChain sends model-generated code derived from the prompt directly to Python exec without first preventing imports or arbitrary execution commands. Exposure requires an application to pass attacker-controlled prompts to a PALChain instance; successful exploitation runs code with the application's privileges.
The record
- CVE
- CVE-2023-36188
- Published
- Jul 6, 2023
- Updated
- Nov 19, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-74, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 6, 2023CVE publishedPublication date reported by the CVE source.
- Nov 19, 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
- PALChain prompt-injection 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