CVE-2026-61439PraisonAI before 4.6.78 Prompt Injection Defense Bypass
Descripción
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.
Datos: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Se publican tal como los indican las fuentes, en inglés.
Productos y versiones afectados
| Fabricante | Producto | Versiones | |
|---|---|---|---|
| MervinPraison | PraisonAI | < 4.6.78, fixed 4.6.78 | |
| praison | praisonai | < 4.6.78 |
Referencias y parches
- GitHub Security Advisory (GHSA-fj8f-m44g-c479) vendor-advisory
- VulnCheck Advisory: PraisonAI before 4.6.78 Prompt Injection Defense Bypass third-party-advisory