ag2ai ag2/autogen SandboxShellTool filter.py ShellAdapter._filter os command injection

Summaryinfo

A vulnerability has been found in ag2ai ag2 and autogen and classified as critical. Affected by this issue is the function ShellAdapter._filter of the file ag2/tools/sandbox/filter.py of the component SandboxShellTool. This manipulation causes os command injection. This vulnerability is tracked as CVE-2026-113663. The attack is possible to be carried out remotely. No exploit exists.

Detailsinfo

A vulnerability has been found in ag2ai ag2 and autogen (the affected version unknown) and classified as critical. Affected by this vulnerability is the function ShellAdapter._filter of the file ag2/tools/sandbox/filter.py of the component SandboxShellTool. The manipulation with an unknown input leads to a os command injection vulnerability. The CWE definition for the vulnerability is CWE-78. The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command before it is sent to a downstream component. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

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 contains_shell_operator 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.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-113663 since 10/20/2026. The exploitation appears to be easy. The attack can be launched remotely. Technical details of the vulnerability are known, but there is no available exploit. The pricing for an exploit might be around USD $0-$5k at the moment (estimation calculated on 11/06/2026). The attack technique deployed by this issue is T1202 according to MITRE ATT&CK.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Vendor

• ag2ai

Name

• ag2
• autogen

Website

• Product: https://github.com/ag2ai/ag2/

CPE 2.3info

• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion