Skip to main content
VulnerabilityPublished

CVE-2026-123022: agentscope-ai AgentScope · Command Injection

Source GCVE Database

0
Compare
Authoritative record:CVE-2026-123022· Medium 6.9

Public exploit available · CVSS 6.9 Medium.

Data as of 5 Nov 2026, 16:05 UTC

CVSS 4.0 base score
6.9Medium
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulDB)CVSS 4.06.9
CNA (VulDB)CVSS 3.17.3
CNA (VulDB)CVSS 3.07.3
CNA (VulDB)CVSS 2.07.5
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 5 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: evidence found.

    CVSS exploit maturity: proof of concept public

  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), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 5 Nov 2026.

What to do

Affected software

ProductAffectedFixed in
agentscope-aiAgentScopeAffected
  • 2.0.0 – 2.0.11
12 affected builds
Fixed in–
GitHubagentscope-ai/agentscopepkg:github/agentscope-ai/agentscopeOther threatsAffected
  • 2.0.0 – 2.0.11
12 affected builds
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 fix is not yet officially released; however, a pull request addressing the vulnerability is awaiting acceptance. Until the fix is integrated and deployed, users should consider restricting network access to the MCP Workspace API component or applying other environment-specific mitigations to limit exposure. Monitor the vendor's repository or advisory channels for the official patch release and apply it promptly once available.

Description

A command injection vulnerability exists in agentscope-ai AgentScope up to version 2.0.11 in the subprocess.Popen function within src/agentscope/mcp/_config.py of the MCP Workspace API component. This vulnerability allows remote attackers to execute arbitrary OS commands by manipulating the command argument. Public exploit code is available, and a fix is pending acceptance in a pull request.

References

Community reviews

Loading reviews…