Vulnerabilidad · Publicado 11/07/2026 · Actualizado 01/08/2026
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 p…
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.
Score: 7.5/10 — Severidad: HIGH — Estado NIST: Deferred
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
CWE-1188
Publicado en NIST NVD.