Skip to main content
CVE-2026-113663VulnerabilityPublished

AG2: Newline injection

Affects ag2Source GCVE Database

0
Compare
Authoritative record:CVE-2026-113663· High 8.8

Not known to be exploited · CVSS 8.8 High : upgrade to 1.1.1 soon.

Data as of 10 Nov 2026, 17:35 UTC

CVSS 3.1 base score
8.8High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (GitHub_M)CVSS 3.18.8
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:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 5 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq 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 10 Nov 2026.

What to do

Upgrade ag2 to 1.1.1.

Affected software

ProductAffectedFixed in
PyPIag2Affected
  • >=0.13.2 <1.1.1
Fixed in
  • 1.1.1
PyPIautogenAffected
  • >=0.13.2 <=0.14.1
Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A patch is available in ag2 version 1.1.1 that fixes this vulnerability. Users should upgrade to version 1.1.1 or later to remediate the issue. Until patched, do not rely on the allowed command or readonly restrictions as security boundaries, as they can be bypassed via newline injection.

Description

SandboxShellTool in ag2 versions >=0.13.2 and <1.1.1 allows bypassing command restrictions by embedding newline characters in commands. The tool's filter does not recognize newlines as shell operators, enabling execution of arbitrary shell commands via 'sh -c' despite configured allowlists or readonly restrictions. This leads to full host command execution, not sandboxed, posing a high-severity risk. The issue is fixed in version 1.1.1.

References

Community reviews

Loading reviews…