CVE-2026-113663ag2ai ag2 OS command injection
CVE-2026-113663 is a OS command injection in ag2ai ag2, rated high (8.8 on CVSS 3.1).
Why this priority: High severity, with no exploitation signal yet.
Published · Updated · NVD status: Received
What it is
Input reaches an operating-system command line, letting an attacker run their own commands on the host. A list of forbidden inputs misses some, so a variant gets through.
How it is reached
An attacker can exploit it over the network, with an ordinary user account, and nobody has to click anything.
What an attacker gains
A successful attack can read the data it protects, change data or behaviour and take it offline. In practice, this kind of flaw lets an attacker run commands or code with the privileges of the affected service.
Is it being exploited?
There is no public report of exploitation yet.
What to do
- Upgrade ag2ai ag2 to 1.1.1 or later.
- Until it is patched, review who holds accounts that can reach it.
Description from NVD
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.
What this means for your architecture.
A CVE names a product. Whether it matters depends on where that product sits in your systems: what reaches it, which trust boundary it guards and what it can reach once compromised. Veriom maps your components, their relationships and your trust boundaries from your code, cloud and delivery evidence, so you can see where a component like this sits. The radar itself does not look at your systems.
Components it touches
- Application servers and the hosts they run on. The flaw sits between untrusted input and code or command execution.
- Template engines. The flaw sits between untrusted input and code or command execution.
- Interfaces that accept external input. The flaw sits at the input boundary of the affected component.
Trust boundaries in play
- Authenticated network access. An account is needed, so exposure follows who can sign in: customers, partners or staff.
- Between untrusted input and code or command execution. An attacker who crosses it can run commands or code with the privileges of the affected service.
- At the input boundary of the affected component. An attacker who crosses it can drive the component into behaviour its authors did not intend.
Questions to answer about your own systems
- Where does ag2ai ag2 run in your systems, and at which version?
- Which of those instances can be reached from the internet or partner networks?
- What can it reach once compromised: which data stores, secrets and services?
Read more
Sources
- CVE records and CVSS scores from the NVD CVE API. This product uses the NVD API but is not endorsed or certified by the NVD.
- Exploitation status from CISA’s Known Exploited Vulnerabilities catalog.
- Exploit likelihood from FIRST’s Exploit Prediction Scoring System (EPSS), refreshed daily.
- Explanations are written by Veriom from fixed templates over each record’s data, not by a person reviewing each CVE. Descriptions are quoted from the records as published.