PANDASAI · CVE-2023-39661 · AI agents & MCP
NO FIX YET
PandasAI, a Python library that lets users ask questions of their data in natural language, has a flaw in its _is_jailbreak check that lets a remote attacker execute arbitrary code. Affected versions are 0.8.1 and earlier.
first public Aug 15, 2023 · 1 public exploit · 2 sources
Check it with your coding agent
It reads this page and tells you if your code or app is affected.
Applications that import pandasai and pass user-supplied prompts into it are the ones exposed, since the flaw sits in the prompt jailbreak check that handles that input. Services that only run pandasai on fixed internal data with no user-written prompts are less exposed. The sources do not state a fixed version.
Not affected if no-user-prompts, version-above-0.8.1
Who cares data-analysis, llm, pandasai, python
pip show pandasai and confirm whether the installed version is 0.8.1 or earlier.0.8.1.No fix yet, per the sources.
An issue in pandas-ai v.0.8.1 and before allows a remote attacker to execute arbitrary code via the _is_jailbreak function.
This page as .md · .json · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub Advisory Database, CC-BY 4.0 · NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.
Are you affected?
Ask from here. InfraStack checks the affected versions against your stack and answers in your inbox.
InfraStack checks the affected versions against your stack and answers in Slack, with the evidence and the fix.
InfraStack checks it against your stack and answers on your report, with the evidence and the fix.