Is there a public exploit for CVE-2026-113663?

No public exploit for CVE-2026-113663 was found in Exploit-DB, Metasploit, Nuclei templates or public proof-of-concept repositories. That is an absence of evidence rather than proof that none exists.

How severe is CVE-2026-113663?

CVE-2026-113663 scores CVSS 8.8 (v3.1), rated high.

What does CVE-2026-113663 affect?

CVE-2026-113663 affects ag2ai autogen, ag2. It is part of the AI and agent stack (AutoGen).

8.8 High

AG2 is an open-source AgentOS.

CVE-2026-113663

AG2 is an open-source AgentOS. From 0.13.2 until ag2 1.1.1, and from autogen 0.13.2 to 0.14.1, SandboxShellTool configurations using allowed=[...] or readonly=True rely on ShellAdapter.filter and containsshelloperator in ag2/tools/sandbox/filter.py and ag2/tools/sandbox/adapter/shell.py to validate a command prefix and reject selected shell syntax. The filter omits newline and carriage-return separators, while the accepted raw string is passed to sh -c, allowing an attacker-influenced agent command to execute an additional arbitrary statement. With the default LocalEnvironment backend, the injected statement runs as a host subprocess with the privileges of the agent process and can affect confidentiality, integrity, and availability. This issue is fixed in ag2 version 1.1.1.

Part of the AI stack

This affects AutoGen, in Agent frameworks.

Assessment

CVSS: 8.8 (v3.1)
Severity: High
Known exploited: Not listed in CISA KEV
Exploit availability: Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
Published: 5 November 2026
Last updated: 5 November 2026
Affected: ag2ai · ag2 · autogen
Assigner: GitHub_M

CVSS vectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

At the source

EUVD (ENISA)

References

Community proofs of concept

No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.

Submit a proof of concept

Only for publicly disclosed vulnerabilities, and only material from testing you were authorised to perform. This platform does not buy, sell, or broker exploits — see earning from vulnerability research for legitimate bounty programs. Submissions are reviewed before they appear. Text only; do not include live credentials, personal data, or anything targeting systems you are not permitted to test.

Title *

Proof of concept *

Write-up (optional)

Affected versions (optional)

Name or handle (optional)

References (optional, one URL per line)

Licence for your contribution *

Private contact (optional, never shown)

Before you submit * This vulnerability is already publicly disclosed (it has a published CVE). This material comes only from testing I was authorised to perform. I have the legal right to publish this content and am not breaching any agreement by doing so. It contains no live credentials, personal data, or anything targeting systems I am not authorised to test. I understand it will be reviewed before it appears publicly and may be rejected. I agree to the submission terms.

What is 7 + 2? *

Query this programmatically

Agents can read this through the MCP endpoint, or over HTTP:

curl https://cve.zerocrew.in/api/cve/CVE-2026-113663