---
id: GHSA-5r2q-3wg3-57m2
title: >-
  Duplicate Advisory: PraisonAI: Prompt Injection Defense Bypassed for
  HIGH-Level Threats
summary: >-
  Duplicate Advisory: PraisonAI: Prompt Injection Defense Bypassed for
  HIGH-Level Threats
severity: high
cvss: 7.5
cwe:
  - CWE-1188
vendor: praisonai
product: praisonai
ecosystem: pip
affected:
  - praisonai <= 4.6.77
published: '2026-07-11'
updated: '2026-10-07'
sourceUpdated: '2026-10-07T20:43:46Z'
source: GHSA
sourceUrl: 'https://github.com/advisories/GHSA-5r2q-3wg3-57m2'
references:
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fj8f-m44g-c479
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-61439'
  - url: >-
      https://www.vulncheck.com/advisories/praisonai-before-prompt-injection-defense-bypass
  - url: 'https://github.com/advisories/GHSA-5r2q-3wg3-57m2'
tags:
  - ghsa
  - pip
ingestedAt: '2026-10-07T20:46:46.981Z'
---

## Overview

### Duplicate Advisory
This advisory has been withdrawn because it is a duplicate of GHSA-fj8f-m44g-c479. This link is maintained to preserve external references.

### Original Description
PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.

## Affected packages

- `praisonai <= 4.6.77`

## Remediation

Refer to the advisory for the patched release.