PandasAI interactive prompt function Remote Code Execution (RCE)
CVE-2024-12366 · GHSA-vv2h-2w3q-3fx7 · published 2025-02-11 · updated 2026-11-16
- Severity
- Critical
- CVSS score
- 9.8
- Chance of exploitation (EPSS)
- 1.2%
- Fixed in
- No fix yet
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Total
- CISA SSVC
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. The security controls of PandasAI (2.4.3 and earlier) fail to distinguish between legitimate and malicious inputs, allowing the attackers to manipulate the system into executing untrusted code, leading to untrusted code execution (RCE), system compromise, or pivoting attacks on connected services.
No fixed release is listed yet for pandasai. Follow the source advisory for updates, and until one ships:
General guidance from ShieldPi, not a vendor fix
- Command or code injection. Remove or disable the affected server or tool, or run it in a sandbox with no secrets in its environment.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| pandasai | PyPI | <= 2.4.2 | No fix yet |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalCode execution in pandasaipandasai
- CriticalPandasAI vulnerable to arbitrary code executionpandasai
- Highpandasai vulnerable to prompt injectionpandasai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.