# PraisonAI Vulnerable to Arbitrary File Write / Path Traversal in Action Orchestrator

Advisory record · `GHSA-jfxc-v5g9-38xr`

- **Identifiers:** `GHSA-jfxc-v5g9-38xr` · `CVE-2026-39305` · `PYSEC-2026-475`
- **State:** Confirmed
- **Severity:** CVSS 9.0 Critical
- **Critical:** Yes: CVSS 9+
- **Weakness (CWE):** [CWE-22](https://cwe.mitre.org/data/definitions/22.html)
- **Tags:** [Path traversal](https://agentprime.io/advisories/tag/path-traversal.md)
- **Published:** 6 Apr 2026
- **Updated:** 16 Nov 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 6 Apr 2026, 23:09 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 9.0: 9.0 or more.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `praisonai` (PyPI): affected `<4.5.113`; fixed in `4.5.113`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> The PraisonAI package (PyPI praisonai) before 4.5.113 has a path traversal flaw in its Action Orchestrator feature, which does not confine file creation and edit actions to the configured workspace directory. An attacker who can supply action steps, or a compromised agent, can write to arbitrary files on the host, which the source says could lead to remote code execution. Upgrade praisonai to version 4.5.113 or later.

Written 6 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 9.0 Critical, CVSS 3.1: `CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:N/I:H/A:H`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0032, the 25th percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 6 Apr 2026, 23:09 UTC: [Confirmed by GitHub Advisory Database](https://github.com/advisories/GHSA-jfxc-v5g9-38xr)
- 31 Oct 2026, 15:04 UTC: First seen by agentprime
- 31 Oct 2026, 15:04 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/PYSEC-2026-475)

## Sources

- [GitHub Advisory Database: GHSA-jfxc-v5g9-38xr](https://github.com/advisories/GHSA-jfxc-v5g9-38xr)
- [OSV: GHSA-jfxc-v5g9-38xr](https://osv.dev/vulnerability/GHSA-jfxc-v5g9-38xr)
- <https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-jfxc-v5g9-38xr>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-39305>
- <https://github.com/MervinPraison/PraisonAI>
- <https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.113>
- <https://github.com/pypa/advisory-database/tree/main/vulns/praisonai/PYSEC-2026-475.yaml>
- <https://pypi.org/project/praisonai>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-jfxc-v5g9-38xr>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-jfxc-v5g9-38xr/>. Everything for agents: <https://agentprime.io/llms.txt>.
