Quick answers
- Is CVE-2026-123023 exploited in the wild?
- No. Junglewise Threat Intelligence has no report of CVE-2026-123023 being exploited in the wild.
- How severe is CVE-2026-123023?
- High severity, with a CVSS score of 7.3, published 5 November 2026.
- Which products and versions are affected?
- Agentscope-Ai AgentScope up to 2.0.8.
- Is there a fix for CVE-2026-123023?
- Yes: fixed in 2.0.9. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
- How is CVE-2026-123023 attacked?
- It is attacked over the network, in a software library.
- Am I affected by CVE-2026-123023?
- Check whether you run Agentscope-Ai AgentScope at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.
How to fix
- Fixed in: 2.0.9
Technical details
The check_permissions function in src/agentscope/tool/_builtin/_bash.py contains incorrect authorization logic that fails to properly validate permissions before command execution. This is a remote exploitation vulnerability affecting the Bash Tool component. A patch has been released and upgrading to version 2.0.9 mitigates the issue.
Affected products
- agentscope-ai AgentScope up to 2.0.8
Timeline
- 2026-11-05: disclosed
- 2026-11-05: patched: Fixed in version 2.0.9 (commit 6b43b13a46401e86abd3defeed9a8bfe5b37bc6d)