Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| MervinPraison / PraisonAI | affected 0 before 4.6.78; unaffected 4.6.78 |
CWE
CWE-693
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4r3p-w3mc-5v34
- https://www.vulncheck.com/advisories/praisonai-before-prompt-injection-defense-bypass
ADP enrichment
No English description supplied.