PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

10.0 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

EPSS

• CVE-2026-34938: 13.40% estimated exploitation activity in the next 30 days; percentile 96.43 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary executecode() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the safegetattr wrapper, achieving arbitrary OS command execution on the host. Details pythontools.py:20 (source) - pythontools.py:22 (guard bypass) - pythontools.py:161 (sink) PoC Impact Any user or agent pipeline running executecode() is exposed to full OS command execution as the process user. Deployments using bot.py, autonomymode.py, or botscli.py set PRAISONAIAUTOAPPROVE=true by default, meaning no human confirmation is required and the tool fires silently when triggered via indirect prompt injection.

Published by the source

1 Apr 2026, 23:17 UTC

Last modified by the source

29 Jun 2026, 12:26 UTC

Source last checked

26 Oct 2026, 13:40 UTC

1. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-6vh2-h83c-9294

2. Revision 2 · amended · 24 Oct 2026

   Amended from osv record GHSA-6vh2-h83c-9294

3. Revision 1 · created · 23 Oct 2026

   Published from ghsa record GHSA-6vh2-h83c-9294

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-34938

Advisory: PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code
IDs: CVE-2026-34938, GHSA-6vh2-h83c-9294
Record: https://patchnext.com/advisories/cve-2026-34938 (revision 3, source checked 26 Oct 2026, 13:40 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Critical (CVSS 10.0)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: praisonaiagents 1.5.90. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI praisonaiagents: affected <= 1.5.89; fixed in 1.5.90

## Suggested inspection (read-only)
- `python -m pip show praisonaiagents`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on praisonaiagents.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-6vh2-h83c-9294 (GitHub-reviewed advisory GHSA-6vh2-h83c-9294 lists affected ranges: PyPI praisonaiagents >=0 <=1.5.89)
- Verified: https://osv.dev/vulnerability/GHSA-6vh2-h83c-9294 (OSV record GHSA-6vh2-h83c-9294 lists affected ranges: PyPI praisonaiagents >=0 <1.5.90 (fixed))

Commands are suggestions: review each one before running it.