PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.
| Vendor | Product | Versions |
|---|---|---|
| mervinpraison | praisonai | 0 |
Updated severity to CRITICAL and corrected exploit availability to false.
Initial creation
