CVE-2026-61439 — PraisonAI before 4.6.78 Prompt Injection Defense Bypass
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…
Published: 2026-07-11 · CVSS: 8.7 · CVSS 4.0
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7