# CVE-2026-40088: MervinPraison PraisonAI OS command injection in execute_command

Source: https://junglewise.ai/threats/cve-2026-40088-mervinpraison-praisonai-os-command-injection-in-execute-command  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-04-09. Updated: 2026-05-10  
License: CC BY 4.0 with a link back

CVE-2026-40088 · Severity: critical · CVSS 9.6 · Published 2026-04-09

PraisonAI, an AI agent framework, is vulnerable to a security flaw that allows attackers to execute unauthorized commands on the underlying system. By providing malicious input through workflow files, agent configurations, or even manipulated AI prompts, an attacker can gain full control over the environment where the software is running. This could lead to the theft of sensitive data, such as SSH keys and passwords, or the complete disruption of business operations.

Technologies: [Praisonai](https://junglewise.ai/threats/technologies/praisonai), [praisonai (PyPI)](https://junglewise.ai/threats/technologies/pypi-praisonai). Vendors: [Praison](https://junglewise.ai/threats/vendors/praison), [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-40088 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-40088 being exploited in the wild.

**How severe is CVE-2026-40088?** Critical severity, with a CVSS score of 9.6, published 9 April 2026.

**Which products and versions are affected?** praisonai (PyPI) ECOSYSTEM:introduced=0,fixed=4.5.121.

**Is there a fix for CVE-2026-40088?** Yes. praisonai (PyPI): upgrade to 4.5.121 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-40088 attacked?** It is attacked over the network or with local access, in a software library.

**Am I affected by CVE-2026-40088?** Check whether you run Praisonai or praisonai (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- praisonai (PyPI): upgrade to 4.5.121 or later

  ```sh
  pip install "praisonai>=4.5.121"
  ```


## Technical details

PraisonAI's workflow system and command execution tools (specifically the `execute_command` function and `_exec_shell` method) pass user-controlled input directly to `subprocess.run()` with `shell=True`. This configuration allows the shell to interpret metacharacters such as `;`, `|`, and `&&`. Attackers can exploit this by supplying malicious strings in YAML workflow steps, `agents.yaml` task descriptions, or via prompt injection that influences LLM-generated tool parameters. Successful exploitation results in arbitrary code execution (RCE) with the privileges of the application process. The vulnerability is addressed in version 4.5.121 by disabling shell execution by default and improving input validation.

## Affected products

- MervinPraison PraisonAI < 4.5.121

## Identifiers

- CVE-2026-40088
- GHSA-2763-cj5r-c79m
- PYSEC-2026-461

## Timeline

- 2026-04-08: disclosed
- 2026-04-08: patched: Fixed in version 4.5.121
- 2026-04-08: advisory

## References

- [https://api.github.com/users/l3tchupkt](https://api.github.com/users/l3tchupkt)
- [https://github.com/l3tchupkt](https://github.com/l3tchupkt)
- [https://api.github.com/users/l3tchupkt/gists%7B/gist_id%7D](https://api.github.com/users/l3tchupkt/gists%7B/gist_id%7D)
- [https://api.github.com/users/l3tchupkt/repos](https://api.github.com/users/l3tchupkt/repos)
- [https://avatars.githubusercontent.com/u/191794587?v=4](https://avatars.githubusercontent.com/u/191794587?v=4)
- [https://api.github.com/users/l3tchupkt/events%7B/privacy%7D](https://api.github.com/users/l3tchupkt/events%7B/privacy%7D)

## Related threats

- [PraisonAI authentication bypass in A2U event streaming](https://junglewise.ai/threats/cve-2026-57146-praisonai-a2u-incomplete-authentication-fix-leaves-current-serve)
- [PraisonAI sandbox escape when Landlock unavailable](https://junglewise.ai/threats/cve-2026-57144-praisonai-sandlocksandbox-falls-back-to-unrestricted-subprocess)
- [PraisonAI recipe policy bypass via YAML-approved tools](https://junglewise.ai/threats/cve-2026-57142-praisonai-recipe-workflow-policy-can-be-bypassed-by-declaring-and)
- [PraisonAI shell command injection in compute-bridged file tools](https://junglewise.ai/threats/cve-2026-57117-praisonai-compute-bridged-file-tools-allow-shell-command)
- [PraisonAI AgentOS authentication bypass in FastAPI deployment](https://junglewise.ai/threats/cve-2026-57116-praisonai-agentos-remains-unauthenticated-after-incomplete-fix)