8 matches found
CVE-2026-51857
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary...
CVE-2026-51858
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, TerminalToolkit.shellexec allows prompt-driven shell command execution without an approval boundary...
CVE-2026-51858
The camel-ai camel software versions v0.2.91a1 , v0.2.91a2 , and v0.2.91a3 are vulnerable to arbitrary shell command execution. The root cause is located in the TerminalToolkit.shell_exec function, which allows prompt-driven command execution without an approval boundary . This flaw falls under C...
EUVD-2026-90423
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary...
CVE-2026-51857
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary...
CVE-2026-51857
The camel-ai camel library (versions v0.2.91a1 , v0.2.91a2 , and v0.2.91a3 ) contains a vulnerability where the CodeExecutionToolkit can execute Python code produced by a model via the SubprocessInterpreter without an approval boundary . This lack of control over generated code execution (CWE-94)...