CVE-2023-39660: Pandasai Pandasai Vulnerable To Prompt Injection Vulnerability

HIGH
Advisory Identifier: GHSA-w832-v3c6-m6rg
Share
CWE-94
Published
Advisory Summary

CVE-2023-39660 is a HIGH pandasai vulnerable to prompt injection vulnerability (CWE-94: Improper Control of Generation of Code ('Code Injection')) affecting Pandasai libraries in the PyPI ecosystem. The issue involves pandasai vulnerable to prompt injection. Remediation is available by upgrading affected packages to version 0.8.1.

CVE-2023-39660 at a Glance

CVE Identifier CVE-2023-39660
GHSA Identifier GHSA-w832-v3c6-m6rg
Severity HIGH
CVSS v3.1 Base Score N/A
CWE Classification CWE-94: Improper Control of Generation of Code ('Code Injection')
Affected Product Pandasai
Package Ecosystem PyPI
Published Date
Last Updated

How to Fix CVE-2023-39660

To remediate this vulnerability, upgrade all affected Pandasai dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

pandasai fixed: 0.8.1 
pip install pandasai>=0.8.1
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release: 

pip show pandasai

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2023-39660, inspect your installed packages using pip:

pip show pandasai

Analyze the terminal output to locate any version of Pandasai in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.8.1), your application is affected.

Note: The pip show pandasai command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-94: Improper Control of Generation of Code ('Code Injection'), where the product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. In Pandasai, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

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.

CVE-2023-39660 Affected Pandasai Versions

1 component(s)
Fixed Versions:
0.8.1
Product / Package Ecosystem Affected Versions Fixed Version
pandasai
pypi/pandasai
PyPI
< 0.8.1
0.8.1

References

NVD — CVE-2023-39660 NVD
https://nvd.nist.gov/vuln/detail/CVE-2023-39660
Pandasai Source Repository REPOSITORY
https://github.com/gventuri/pandas-ai/issues/399
Pandasai Source Repository REPOSITORY
https://github.com/gventuri/pandas-ai/pull/409
Security Fix Commit FIX COMMIT
https://github.com/gventuri/pandas-ai/commit/3aac79be8fc1d18b53d66a566adddbbdd2b38ad5
Pandasai Source Repository REPOSITORY
https://github.com/gventuri/pandas-ai

Frequently Asked Questions

What is CVE-2023-39660?
CVE-2023-39660 is a security vulnerability in Pandasai involving pandasai vulnerable to prompt injection under CWE-94: Improper Control of Generation of Code ('Code Injection').
Which Pandasai versions are affected?
Affected versions include releases prior to 0.8.1 across affected packages: pandasai.
What version fixes CVE-2023-39660?
Upgrading to 0.8.1 (or the latest patched release for your respective branch) resolves the vulnerability.
Is pandasai affected?
Yes, pandasai is affected in releases prior to 0.8.1. Upgrade your dependency to 0.8.1 or later.
What CWE is associated with CVE-2023-39660?
CVE-2023-39660 is classified under CWE-94: Improper Control of Generation of Code ('Code Injection') (The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.).
How can I check PyPI dependencies for CVE-2023-39660?
Run the dependency tree command: 'pip show pandasai'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
View Raw JSON 
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-w832-v3c6-m6rg",
  "modified" : "2023-08-21T20:46:52Z",
  "published" : "2023-08-21T18:31:23Z",
  "aliases" : [ "CVE-2023-39660" ],
  "summary" : "pandasai vulnerable to prompt injection",
  "details" : "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.",
  "severity" : [ ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "pandasai"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "0.8.1"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2023-39660"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/gventuri/pandas-ai/issues/399"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/gventuri/pandas-ai/pull/409"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/gventuri/pandas-ai/commit/3aac79be8fc1d18b53d66a566adddbbdd2b38ad5"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/gventuri/pandas-ai"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-94" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2023-08-21T20:46:52Z",
    "nvd_published_at" : "2023-08-21T17:15:48Z"
  }
}