pandasai
4 published advisories; version 0.8.1 or later fixes all but 3 of them.
- Registry
- PyPI
- Advisories
- 4
- Latest fix
- 0.8.1
- Exploited in the wild
- None listed
3 advisories have no fixed release in any version yet. What can be done meanwhile:
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.GHSA-vv2h-2w3q-3fx7 · GHSA-5g73-69p4-7gvx · GHSA-8fp9-43pw-56vw
Check your projects
shieldpi agent-config checks agent and MCP packages from npm and PyPI, not pandasai. Any scanner that reads the OSV database finds it in your lockfiles, for example Google's open-source OSV-Scanner.
osv-scanner scan source -r .Or check a lockfile against ShieldMap in your browser.
Packages reported malicious by OpenSSF whose names imitate pandasai. Check that you install pandasai itself.
- pandaai 1 letter off
- pandaas 2 letters off
- pandsa 2 letters off
Source: github.com/sinaptik-ai/pandas-ai, named in the package metadata (not verified)
0 of the last 10 releases of pandasai were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.
- 3.0.0
- 2.3.2
- 2.4.2
- 2.4.1
- 2.4.0
- 2.3.0
- 2.2.15
- 2.2.14
- 2.2.12
- 2.2.11
Green: published with provenance. Grey: without.
OpenSSF Scorecard has not scored this repository.
Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.
| Advisory | Severity | Affected | Fixed in | Published |
|---|---|---|---|---|
| PandasAI interactive prompt function Remote Code Execution (RCE)CVE-2024-12366 | Critical | <= 2.4.2 | No fix yet | 2025-02-11 |
| Code execution in pandasaiCVE-2024-23752 | Critical | <= 1.5.17 | No fix yet | 2024-01-22 |
| pandasai vulnerable to prompt injectionCVE-2023-39660 | High | < 0.8.1 | 0.8.1 | 2023-08-21 |
| PandasAI vulnerable to arbitrary code executionCVE-2023-39661 | Critical | <= 0.8.1 | No fix yet | 2023-08-15 |
Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].