Remote code execution via incomplete AST filtering
Published Aug 15, 2023 · Updated Oct 8, 2024
Code injection in PandasAI 0.9.1 and earlier allows remote attackers to execute arbitrary code through a crafted LLM prompt. The _is_jailbreak function rejects selected dangerous names but permits attribute traversal through subclasses to reach system commands. Exploitation requires an application to pass attacker-controlled prompts to PandasAI and execute the resulting model-generated Python code.
Summary
What happened
Code injection in PandasAI 0.9.1 and earlier allows remote attackers to execute arbitrary code through a crafted LLM prompt. The _is_jailbreak function rejects selected dangerous names but permits attribute traversal through subclasses to reach system commands. Exploitation requires an application to pass attacker-controlled prompts to PandasAI and execute the resulting model-generated Python code.
The record
- CVE
- CVE-2023-39661
- 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.
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
- Prompt jailbreak and AST-filter bypass 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