Remote code execution via LLM-generated Python jailbreak
Published Aug 21, 2023 · Updated Oct 7, 2024
Code injection in pandasai 0.8.0 and earlier allows remote attackers to execute arbitrary code via a crafted prompt request. The prompt reaches an LLM whose generated Python is executed after a code cleaner fails to reject dangerous built-ins and object-subclass access. No authentication or user interaction is required when a deployment exposes the prompt function remotely, and exploitation runs commands with the host process's privileges.
Summary
What happened
Code injection in pandasai 0.8.0 and earlier allows remote attackers to execute arbitrary code via a crafted prompt request. The prompt reaches an LLM whose generated Python is executed after a code cleaner fails to reject dangerous built-ins and object-subclass access. No authentication or user interaction is required when a deployment exposes the prompt function remotely, and exploitation runs commands with the host process's privileges.
The record
- CVE
- CVE-2023-39660
- Published
- Aug 21, 2023
- Updated
- Oct 7, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 21, 2023CVE publishedPublication date reported by the CVE source.
- Oct 7, 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
- PandasAI prompt-injection jailbreak 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