Track vulnerabilities like this one. Sign up free to get alerted when software you use is affected.
9.8

camel-ai camel can run shell commands without approval

CVE-2026-51858 · published 1 month ago
Summary

Versions 0.2.91a1, a2, and a3 of camel-ai camel let a user enter a prompt that triggers the TerminalToolkit.shell_exec function, which executes operating system commands without any check. This could allow an attacker to run arbitrary commands on the server. Upgrade to a patched version or disable the shell_exec feature until a fix is applied.

Original advisory text
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, TerminalToolkit.shell_exec allows prompt-driven shell command execution without an approval boundary.
In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, TerminalToolkit.shell_exec allows prompt-driven shell command execution without an approval boundary.
References
Fix within
Internet-facing 3 days
Internal 60 days
  • Not known to be exploited
  • Can be exploited automatically
  • Gives an attacker full control
Severity
9.8 Critical
Exploitation
<1% chance of attack within 30 days
Type
CWE-94Code Injection
Timeline
Published30 Sep 2026
Updated4 Nov 2026
First seen30 Sep 2026
Sources
CVE-2026-51858 · NVD
CVE-2026-51858 · MITRE
Track software like this
Free during beta