CyberRota Analysis
AI-GeneratedPraisonAI versions prior to 1.6.78 are vulnerable due to improper caching of tool approval decisions, which allows attackers to exploit initial benign approvals to perform unauthorized file write operations with arbitrary parameters. This could lead to significant security breaches, as malicious actions can be executed without proper review. Organizations using affected versions should prioritize this vulnerability to mitigate the risk of unauthorized access and data manipulation.
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 1.6.78 caches tool approval decisions by tool name only, allowing attackers to reuse initial approvals for subsequent calls with arbitrary arguments. Attackers can exploit this by obtaining approval for a benign operation and then executing dangerous file write operations with unreviewed parameters in the same session.