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.
Metrics
Affected Vendors & Products
| Vendors | Products |
|---|---|
| Praison |
|
No data.
No data.
No data.
References
History
Sat, 11 Jul 2026 13:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | 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. | |
| Title | PraisonAI before 4.6.78 Prompt Injection Defense Bypass | |
| First Time appeared |
Praison
Praison praisonai |
|
| Weaknesses | CWE-1188 | |
| CPEs | cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:* | |
| Vendors & Products |
Praison
Praison praisonai |
|
| References |
| |
| Metrics |
cvssV3_1
|
MITRE
Status: PUBLISHED
Assigner: VulnCheck
Published:
Updated: 2026-07-11T13:01:03.106Z
Reserved: 2026-07-09T14:05:47.928Z
Link: CVE-2026-61439
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.