CVE-2026-61439
MervinPraison PraisonAI 취약점
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.
- 대응 우선순위
- 점검
- CVSS
- 8.7
- EPSS
- 0.26% 백분위 17.5% · 2026.07.15 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.07.11