CyberRota Analysis
AI-GeneratedOllama versions prior to 0.31.2 are vulnerable due to an incorrect authorization flaw in the Bash tool approval mechanism, which inadequately parses shell syntax. This allows attackers to exploit prompt injection to execute arbitrary shell commands by appending control operators to approved commands, effectively bypassing session approval. Organizations using affected versions should prioritize remediation to mitigate the risk of unauthorized command execution.
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
Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by appending control operators like semicolons or logical operators to approved commands, bypassing the session approval requirement.