CVE-2026-113663: ag2ai ag2 · OS Command Injection
Affects ag2ai ag2Source CVE Database V5
Not known to be exploited · CVSS 8.8 High : upgrade to 1.1.1 soon.
Data as of 5 Nov 2026, 23:04 UTC
Thin evidence
One scorer or none| CNA (GitHub_M) | CVSS 3.1 | 8.8 |
|---|
- Patch
- Available – fixed in 1.1.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 5 Nov 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 5 Nov 2026.
What to do
Upgrade ag2ai ag2 to 1.1.1.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| ag2aiag2 | Affected
| Fixed in
|
| ag2aiautogen | Affected
| Fixed in– |
AI-suggested
Upgrade ag2 to version 1.1.1 or later, where this vulnerability is fixed. No other mitigations are specified or recommended by the vendor advisory.
Description
CVE-2026-113663 is an OS command injection vulnerability in the open-source AgentOS project ag2. Versions from 0.13.2 up to but not including 1.1.1 are affected. The vulnerability arises because the ShellAdapter filtering mechanism fails to block newline and carriage-return characters, allowing an attacker to inject additional shell commands. This can lead to arbitrary command execution with the privileges of the agent process, impacting confidentiality, integrity, and availability. The issue is fixed in ag2 version 1.1.1.