RCE in Aliasrobotics Cai
CVE-2025-67511
Cybersecurity AI (CAI) is an open-source framework for building and deploying AI-powered offensive and defensive automation. Versions 0.5.9 and below are vulnerable to Command Injection through the run_ssh_command_with_credentials() function, which is available to AI agents. Only password and command inputs are escaped in run_ssh_command_with_credentials to prevent shell injection; while username, host and port values are injectable. This issue does not have a fix at the time of publication.
Vulnerability class: Command Injection (OS Command Injection)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.6 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.020, 81.3th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Aliasrobotics Cai — versions <= 0.5.9
- Aliasrobotics Cybersecurity Ai
Weakness classification (CWE)
Public exploits and proof-of-concept code
1 public repository with exploit or proof-of-concept code for this CVE:
- edoardottt/CVE-2025-67511 (7 stars, last pushed 2026-06-15): CVE-2025-67511: Tricking a Security AI Agent Into Pwning Itself
References
- https://github.com/aliasrobotics/cai/security/advisories/GHSA-4c65-9gqf-4w8h (Exploit, Vendor Advisory)
- https://github.com/aliasrobotics/cai/commit/09ccb6e0baccf56c40e6cb429c698750843a999c (Patch)
- https://www.hacktivesecurity.com/blog/2025/12/10/cve-2025-67511-tricking-a-security-ai-agent-into-pwning-itself (Exploit, Third Party Advisory, Press/Media Coverage)
This CVE has public exploit evidence. See the latest CVEs with public exploits.