CVE-2023-39660
pandasai vulnerable to prompt injection
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
NVD Score used
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.
- Record
CVE-2023-39660- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
CVE List No score
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.
- Record
CVE-2023-39660- Weakness
- CWE-94
- Updated
- 2026-11-02
EUVDEUVD-2023-2372 No score
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.
- Record
EUVD-2023-2372- Updated
- 2026-11-03
GitHub AdvisoriesGHSA-w832-v3c6-m6rg No score
pandasai vulnerable to prompt injection
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.
- Record
GHSA-w832-v3c6-m6rg- Weakness
- CWE-94
- Updated
- 2026-11-02
OSV No score
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.
- Record
CVE-2023-39660- Updated
- 2026-11-02
OSVGHSA-w832-v3c6-m6rg No score
pandasai vulnerable to prompt injection
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.
- Record
GHSA-w832-v3c6-m6rg- Weakness
- CWE-94
- Updated
- 2026-11-02
OSVPYSEC-2026-1757 No score
pandasai vulnerable to prompt injection
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.
- Record
PYSEC-2026-1757- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
pandasaiPyPI |
before 0.8.1 | 0.8.1 |
pandasaiPyPI |
before 0.8.1, plus listed versions 0.0.10.0.20.0.30.1.00.1.1 Show 44 moreShow less0.2.00.2.10.2.100.2.110.2.120.2.130.2.140.2.150.2.160.2.20.2.30.2.40.2.50.2.60.2.70.2.80.2.90.3.00.4.00.4.10.4.20.5.00.5.10.5.20.5.30.5.40.5.50.6.00.6.10.6.100.6.110.6.120.6.20.6.30.6.40.6.50.6.60.6.70.6.80.6.90.7.00.7.10.7.20.8.0 |
0.8.1 |
History
| Recorded | Changed | Sources |
|---|---|---|
| aliases | EUVD | |
| first indexed | CVE List, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2023-39660 is a critical vulnerability (CVSS 9.8) in Gabrieleventuri Pandasai, published August 21, 2023. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 1.53%, the 74th percentile. Fixed in pandasai 0.8.1.
References
github.com/gventuri/pandas-ai/issues/399
nvd.nist.gov/vuln/detail/CVE-2023-39660
pypi.org/project/pandasai