CyberRota Analysis
AI-GeneratedPraisonAI versions prior to 4.6.78 are vulnerable to a prompt injection defense bypass, allowing attackers to exploit single or double-vector prompt injections classified as HIGH threat level. This vulnerability can enable unauthorized access to the model, potentially compromising its integrity and functionality. Organizations using affected versions should prioritize updating to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
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.