# CVE-2026-56693: nanocoai NanoClaw privilege escalation in create_agent handler

Source: https://junglewise.ai/threats/cve-2026-56693-nanocoai-nanoclaw-privilege-escalation-in-create-agent-handler  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-23. Updated: 2026-06-23  
License: CC BY 4.0 with a link back

CVE-2026-56693 · Severity: medium · CVSS 5.5 · Published 2026-06-23

NanoClaw, a platform for managing autonomous agent containers, contains a security flaw that allows restricted agents to bypass their isolation. By exploiting this vulnerability, a confined agent can create unauthorized new agent groups and configurations, potentially gaining higher-level access to the system's central database. This could allow an attacker to escalate their privileges and interfere with the management of other agents or system resources.

## Quick answers

**Is CVE-2026-56693 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-56693 being exploited in the wild.

**How severe is CVE-2026-56693?** Medium severity, with a CVSS score of 5.5, published 23 June 2026.

**Which products and versions are affected?** nanocoai nanoclaw < 2.1.17.

**Is there a fix for CVE-2026-56693?** A patch was published on 2026-06-09: Fix merged into main branch via PR #2720 Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-56693 attacked?** It is attacked with local access, in a software library.

**Am I affected by CVE-2026-56693?** Check whether anything you run is named in the advisory. 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.

## Technical details

A privilege escalation vulnerability exists in NanoClaw's 'create_agent' delivery-action handler due to improper client-side enforcement of server-side security (CWE-602). The root cause is a lack of host-side authorization checks; the system previously relied on the untrusted agent container to gate access to the 'create_agent' tool. An attacker with low-privileged access within a confined agent container can manually invoke the 'create_agent' action to perform unauthorized writes to the central database, including 'agent_groups', 'container_configs', and 'agent_destinations'. This allows the attacker to escalate beyond their intended confinement boundary. The issue is resolved in version 2.1.17 by implementing host-side CLI scope verification.

## Affected products

- nanocoai nanoclaw < 2.1.17

## Timeline

- 2026-06-09: patched: Fix merged into main branch via PR #2720
- 2026-06-23: disclosed: CVE-2026-56693 published

## References

- [https://github.com/nanocoai/nanoclaw/commit/ac37ecbfd6b9d14fdfa1598a6412a8ffdbeaef45](https://github.com/nanocoai/nanoclaw/commit/ac37ecbfd6b9d14fdfa1598a6412a8ffdbeaef45)
- [https://github.com/nanocoai/nanoclaw/pull/2720](https://github.com/nanocoai/nanoclaw/pull/2720)
- [https://www.vulncheck.com/advisories/nanoclaw-privilege-escalation-via-unauthorized-create-agent-system-action](https://www.vulncheck.com/advisories/nanoclaw-privilege-escalation-via-unauthorized-create-agent-system-action)