---
title: "CVE-2026-57145: PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation"
url: https://erroneo.us/security/cve/CVE-2026-57145/
description: "CVE-2026-57145 (praisonai (PyPI)): PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the…"
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-2026-57145"
kev: false
cvss: 9.1
epss: 0.00544
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-57145: PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

**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?

- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 0.5% , percentile 45: FIRST’s model estimates a 0.5% chance of exploitation activity in the next 30 days, higher than 45% 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) < 4.6.61, fixed in 4.6.61 . Check your lockfile, including transitive dependencies.

## What it is

PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks. Prompt-influenced agents can read files through edit and diff behavior or overwrite files accessible to the process, exposing secrets and enabling persistence or application tampering. This issue is fixed in 4.6.62.

## Affected packages

- PyPI `praisonai` < 4.6.61 → fixed: 4.6.61

## Affected products (CVE record)

- MervinPraison PraisonAI: < 4.6.62

## Severity

- GitHub_M CVSS 3.1: 9.1 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N`
- GitHub CVSS 3.1: 9.1 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 0.54% probability of exploitation activity in the next 30 days; percentile 45.

## Sources

- [GitHub Advisory GHSA-29w3-p9w9-wc47](https://github.com/advisories/GHSA-29w3-p9w9-wc47)
- [CVE.org record CVE-2026-57145](https://www.cve.org/CVERecord?id=CVE-2026-57145)
- [NVD entry CVE-2026-57145](https://nvd.nist.gov/vuln/detail/CVE-2026-57145)
- [github.com](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-29w3-p9w9-wc47)
- [github.com](https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33)
- [github.com](https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62)

---
Source page: https://erroneo.us/security/cve/CVE-2026-57145/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt