| ID |
CVE-2026-61439
|
| Sažetak |
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. |
| Reference |
|
| CVSS |
| Base: | 7.5 |
| Impact: | 3.6 |
| Exploitability: | 3.9 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
NONE |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| HIGH |
NONE |
NONE |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
| Zadnje važnije ažuriranje |
13-07-2026 - 18:05 |
| Objavljeno |
11-07-2026 - 14:16 |
