Remote code execution via unvalidated CPAL prompts
Published Aug 15, 2023 · Updated Oct 9, 2024
Code injection in LangChain before 0.0.247 allows remote attackers to execute arbitrary Python code through a crafted CPALChain prompt. CPALChain places prompt-derived causal operations in EntityModel.code, and StoryModel._forward_propagate executes each generated string with Python exec() without validation. Exploitation requires an application to expose CPALChain prompt input to untrusted remote users; successful code runs with the hosting Python process's privileges.
Summary
What happened
Code injection in LangChain before 0.0.247 allows remote attackers to execute arbitrary Python code through a crafted CPALChain prompt. CPALChain places prompt-derived causal operations in EntityModel.code, and StoryModel._forward_propagate executes each generated string with Python exec() without validation. Exploitation requires an application to expose CPALChain prompt input to untrusted remote users; successful code runs with the hosting Python process's privileges.
The record
- CVE
- CVE-2023-38860
- Published
- Aug 15, 2023
- Updated
- Oct 9, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 15, 2023CVE publishedPublication date reported by the CVE source.
- Oct 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.
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
- CPALChain prompt-injection reproductionproof of concept · unverified
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