CVE-2026-123022agentscope-ai AgentScope command injection
CVE-2026-123022 is a command injection in agentscope-ai AgentScope, rated medium (5.5 on CVSS 4.0).
Why this priority: Some exploitation likelihood, at lower severity.
Published · Updated · NVD status: Deferred
What it is
Input ends up inside a command the software runs, so an attacker can add commands of their own. Input reaches an operating-system command line, letting an attacker run their own commands on the host.
How it is reached
An attacker can exploit it over the network, without an account, and nobody has to click anything.
What an attacker gains
The direct impact is limited: partial access to data or a partial outage. 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. It can be exploited automatically, at scale. EPSS estimates a 1.6% chance of exploitation activity in the next 30 days, higher than 77% of scored CVEs.
What to do
- No fixed version is listed yet. Find every place agentscope-ai AgentScope runs, watch the references for a fix, and plan a replacement if it is no longer supported.
- While there is no fix, keep it off the internet or behind a VPN, allowlist or authenticating proxy.
Description from NVD
A vulnerability was detected in agentscope-ai AgentScope up to 2.0.11. The impacted element is the function subprocess.Popen of the file src/agentscope/mcp/_config.py of the component MCP Workspace API. The manipulation of the argument command results in os command injection. The attack may be launched remotely. The exploit is now public and may be used. The pull request to fix this issue awaits acceptance.
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.
Trust boundaries in play
- Internet-facing entry points. No account is needed. Any instance reachable from outside your perimeter, through a load balancer, gateway, VPN or exposed admin port, is in scope.
- 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.
Questions to answer about your own systems
- Where does agentscope-ai AgentScope 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
Patches and commits
Advisories
Issue reports
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.