Description
PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution (RCE) instead of the intended explanation of the natural language processing by the LLM.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| CISA-ADPADP (enrichment) | 3.1 | Critical9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| NVDNVD · Deferred | 3.1 | Critical9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- EPSS (exploitation in 30 days)
- 1.2% · top 31% of all CVEs (5 Nov 2026)
- CISA SSVC
- Exploitation: none · Automatable: yes · Technical impact: total
Loading the EPSS history…
The list uses the assigner's score when there is one, then CISA's, then NVD's: Critical 9.8.
Weakness
- CWE-94 Improper Control of Generation of Code ('Code Injection')
Affected products
- affected 2.4.0
Affected packages
From reviewed advisories of the GitHub Advisory Database.
- PyPIpandasaiGHSA-vv2h-2w3q-3fx7 (opens in a new tab)
References (3)
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisory GHSA-vv2h-2w3q-3fx7 (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://trackcve.app/cve/CVE-2024-12366)Record last updated .