# CVE-2026-51904: SuperAGI improper access control in agent execution controller

Source: https://junglewise.ai/threats/cve-2026-51904-superagi-up-to-v0-0-14-contains-an-improper-access-control  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-02. Updated: 2026-10-05  
License: CC BY 4.0 with a link back

CVE-2026-51904 · Severity: info · Published 2026-10-02

SuperAGI is an AI agent orchestration platform that allows organizations to create and run autonomous agents. A vulnerability in versions up to v0.0.14 allows authenticated users from one organization to create or execute agents belonging to other organizations, potentially exposing sensitive agent definitions and execution data across organizational boundaries.

Technologies: [SuperAGI](https://junglewise.ai/threats/technologies/superagi). Vendors: [SuperAGI](https://junglewise.ai/threats/vendors/superagi).

## Quick answers

**Is CVE-2026-51904 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-51904 being exploited in the wild.

**How severe is CVE-2026-51904?** Informational severity, published 2 October 2026.

**Which products and versions are affected?** SuperAGI up to v0.0.14.

**Is there a fix for CVE-2026-51904?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-51904 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-51904?** Check whether you run SuperAGI 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.

## Technical details

The agent execution controller endpoints /agentexecutions/add and /agentexecutions/add_run in superagi/controllers/agent_execution.py accept a caller-supplied agent_id parameter but fail to verify that the agent belongs to the authenticated user's organization. An authenticated remote attacker can exploit this improper access control via CWE-284 to create or trigger execution records for agents outside their organization's scope.

## Affected products

- SuperAGI SuperAGI up to v0.0.14

## Timeline

- 2026-10-02: disclosed

## References

- [https://gist.github.com/Ro1ME/3f712e2a9f643a08c6c825d25fbfe0e0](https://gist.github.com/Ro1ME/3f712e2a9f643a08c6c825d25fbfe0e0)

## Related threats

- [SuperAGI improper access control in agent execution](https://junglewise.ai/threats/cve-2026-51903-superagi-v0-0-14-contains-an-improper-access-control)
- [SuperAGI authorization bypass in agent scheduling](https://junglewise.ai/threats/cve-2026-51901-superagi-up-to-0-0-14-is-vulnerable-to-incorrect-access-control)
- [SuperAGI incorrect access control in agent endpoints](https://junglewise.ai/threats/cve-2026-51899-in-superagi-v0-0-14-and-prior-controller-endpoints-api-agents)