---
title: "CVE-2026-57125: PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass"
url: https://erroneo.us/security/cve/CVE-2026-57125/
description: "CVE-2026-57125 (praisonai (PyPI)): PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-09-14
date_modified: 2026-09-14
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-57125"
kev: false
cvss: 9.8
epss: 0.00601
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-57125: PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.6% , percentile 48: FIRST’s model estimates a 0.6% chance of exploitation activity in the next 30 days, higher than 48% of all scored CVEs (low). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes praisonai (PyPI) <= 4.6.48, fixed in 4.6.59 ; praisonaiagents (PyPI) < 1.6.59, fixed in 1.6.59 . Check your lockfile, including transitive dependencies.

## What it is

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agentyaml, and the approve field can mark executecommand as YAML-approved before @requireapproval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.

## Affected packages

- PyPI `praisonai` <= 4.6.48 → fixed: 4.6.59
- PyPI `praisonaiagents` < 1.6.59 → fixed: 1.6.59

## Affected products (CVE record)

- MervinPraison PraisonAI: < 4.6.59
- MervinPraison praisonaiagents: < 1.6.59

## Severity

- GitHub_M CVSS 3.1: 9.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`
- GitHub CVSS 3.1: 9.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 0.60% probability of exploitation activity in the next 30 days; percentile 48.

## Sources

- [GitHub Advisory GHSA-4869-x4pr-q22x](https://github.com/advisories/GHSA-4869-x4pr-q22x)
- [CVE.org record CVE-2026-57125](https://www.cve.org/CVERecord?id=CVE-2026-57125)
- [NVD entry CVE-2026-57125](https://nvd.nist.gov/vuln/detail/CVE-2026-57125)
- [github.com](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x)
- [github.com](https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9)
- [github.com](https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59)

---
Source page: https://erroneo.us/security/cve/CVE-2026-57125/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt