Remote code execution via unrestricted LLM-generated Python
Published Mar 28, 2026 · Updated Mar 28, 2026
Code injection in Sinaptik GmbH PandasAI 3.0 allows remote attackers to execute arbitrary host commands through crafted chat messages. CodeExecutor.execute passes LLM-generated Python to native exec with a globals dictionary that omits builtins, so Python supplies unrestricted built-ins. Default Agent instances use no sandbox; any remote party able to submit chat input can run commands with the hosting process's privileges.
Summary
What happened
Code injection in Sinaptik GmbH PandasAI 3.0 allows remote attackers to execute arbitrary host commands through crafted chat messages. CodeExecutor.execute passes LLM-generated Python to native exec with a globals dictionary that omits builtins, so Python supplies unrestricted built-ins. Default Agent instances use no sandbox; any remote party able to submit chat input can run commands with the hosting process's privileges.
The record
- CVE
- CVE-2026-4998
- Published
- Mar 28, 2026
- Updated
- Mar 28, 2026
- Vendor
- Sinaptik GmbH
- Product
- PandasAI
- Classifications
- CWE-74, CWE-94, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 28, 2026CVE publishedPublication date reported by the CVE source.
- Mar 28, 2026Record 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?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=3.0
What conditions does exploitation require?
What is affected?
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
- Remote Code Execution via Default Insecure exec() in CodeExecutorproof 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