# CVE-2026-44336: PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection

> Attackers can exploit path traversal in PraisonAI MCP tools to write malicious .pth files, leading to arbitrary code execution.

- **Severity:** Critical 9.4 (`CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** A user has to click or open something
- **Fix available:** Yes
- **Published:** 8 May 2026
- **Updated:** 11 May 2026
- **Also known as:** GHSA-9mqq-jqxf-grvw, PYSEC-2026-472

## What is CVE-2026-44336?

CVE-2026-44336 is a critical path traversal vulnerability in MervinPraison PraisonAI, published on 8 May 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

### Official description

PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params["arguments"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name="../../<some-path>" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34.

Weakness: CWE-94 (Improper Control of Generation of Code), CWE-913 (Improper Control of Dynamically-Managed Code Resources), CWE-22 (Improper Limitation of a Pathname to a Restricted Directory), CWE-829 (Inclusion of Functionality from Untrusted Control Sphere), CWE-20 (Improper Input Validation)

## Which versions are affected by CVE-2026-44336?

3 open source packages ship an affected version, including praisonai and PraisonAI. It affects 1 product.


| Package | Ecosystem | Affected | Fixed in |
| --- | --- | --- | --- |
| `praisonai` | PyPI | All versions | 4.6.34 |
| `praisonai` | PyPI | All versions | 4.6.34 |
| `PraisonAI` | PyPI | All versions | 4.6.34 |

Products: Praison Praisonai.

## How do I fix CVE-2026-44336?

Upgrade praisonai to 4.6.34 or later.

## Is CVE-2026-44336 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-44336 exists.

## Other vulnerabilities in MervinPraison PraisonAI

- [CVE-2026-39888](https://insights.sbomify.com/CVE-2026-39888/): PraisonAIAgents has a sandbox escape via exception frame traversal in `execute_code` (subprocess mode) (critical 10.0)
- [CVE-2026-41497](https://insights.sbomify.com/CVE-2026-41497/): Incomplete fix for CVE-2026-34935: Command Injection in MervinPraison/PraisonAI (critical 9.8)
- [CVE-2026-40288](https://insights.sbomify.com/CVE-2026-40288/): PraisonAI: Critical RCE via `type: job` workflow YAML (critical 9.8)
- [CVE-2026-39890](https://insights.sbomify.com/CVE-2026-39890/): PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading (critical 9.8)
- [CVE-2026-34934](https://insights.sbomify.com/CVE-2026-34934/): PraisonAI: Second-Order SQL Injection in `get_all_user_threads` (critical 9.8)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-44336 and fix it if it is affected.

What it is: CVE-2026-44336 is a critical path traversal vulnerability in MervinPraison PraisonAI, published on 8 May 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-44336 exists.

Affected packages and fixed versions:
- praisonai (PyPI): affected all versions; fixed in 4.6.34
- praisonai (PyPI): affected all versions; fixed in 4.6.34
- PraisonAI (PyPI): affected all versions; fixed in 4.6.34

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-44336/ (Markdown: https://insights.sbomify.com/CVE-2026-44336/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-44336
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-44336
- OSV: https://osv.dev/vulnerability/CVE-2026-44336

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-44336/
Summaries are generated and may contain mistakes; the official description above is the record.