---
id: CVE-2023-39660
aliases:
  - GHSA-w832-v3c6-m6rg
  - PYSEC-2026-1757
title: pandasai vulnerable to prompt injection
summary: pandasai vulnerable to prompt injection
severity: high
vendor: pandasai
product: pandasai
ecosystem: pip
affected:
  - pandasai < 0.8.1
patched:
  - pandasai 0.8.1
published: '2023-08-21'
updated: '2026-07-07'
source: OSV
sourceUrl: 'https://osv.dev/vulnerability/GHSA-w832-v3c6-m6rg'
references:
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2023-39660'
  - url: 'https://github.com/gventuri/pandas-ai/issues/399'
  - url: 'https://github.com/gventuri/pandas-ai/pull/409'
  - url: >-
      https://github.com/gventuri/pandas-ai/commit/3aac79be8fc1d18b53d66a566adddbbdd2b38ad5
  - url: 'https://github.com/gventuri/pandas-ai'
tags:
  - osv
  - pip
epss: 0.01534
epssPercentile: 0.73719
ingestedAt: '2026-07-08T18:25:53.579Z'
---

## Overview

An issue in Gaberiele Venturi pandasai v.0.8.0 and before allows a remote attacker to execute arbitrary code via a crafted request to the prompt function.

## Affected packages

- `pandasai < 0.8.1`

## Remediation

Upgrade to a patched release:

- `pandasai 0.8.1`