# CVE-2026-90810: CosmicStack mercury-agent authorization bypass in shell command validation

Source: https://junglewise.ai/threats/cve-2026-90810-cosmicstack-mercury-agent-authorization-bypass-in-shell-command  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-14. Updated: 2026-09-26  
License: CC BY 4.0 with a link back

CVE-2026-90810 · Severity: medium · CVSS 6.3 · Published 2026-09-14

Mercury is an AI agent application that executes shell commands on behalf of authenticated users. The shell command permission checker incorrectly classifies `find` commands with dangerous flags (like `-exec`, `-delete`) as safe read-only operations, allowing authenticated attackers to execute arbitrary commands and write files without triggering approval prompts.

Technologies: [Cosmicstack Labs Mercury Agent](https://junglewise.ai/threats/technologies/mercury-agent). Vendors: [Cosmicstack Labs](https://junglewise.ai/threats/vendors/cosmicstack-labs).

## Quick answers

**Is CVE-2026-90810 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-90810 being exploited in the wild.

**How severe is CVE-2026-90810?** Medium severity, with a CVSS score of 6.3, published 14 September 2026.

**Which products and versions are affected?** Cosmicstack Labs Mercury Agent up to 1.1.13.

**Is there a fix for CVE-2026-90810?** 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-2026-90810 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-90810?** Check whether you run Cosmicstack Labs Mercury Agent 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 vulnerability is an improper authorization flaw in the `PermissionManager.checkShellCommand()` function (src/capabilities/permissions.ts). The code maintains a list of SAFE_READ_PATTERNS that includes `find *` as a harmless read-only pattern, but `find` supports write-capable operators like `-exec`, `-execdir`, `-delete`, `-ok`, and `-okdir` that can spawn subprocesses and modify the filesystem. The validator applies only simple pattern matching and does not perform semantic validation of `find`-specific dangerous flags. When an authenticated user sends a chat message containing `find . -maxdepth 0 -exec sh -c 'command' ';'`, the permission layer incorrectly approves it as safe-read and the command is executed via `spawn(command, [], {shell: true})`, bypassing the normal user approval prompt. This affects Mercury up to version 1.1.13. The attack requires prior authentication to the web interface.

## Affected products

- CosmicStack Labs mercury-agent up to 1.1.13

## Timeline

- 2026-09-14: disclosed: Published on NVD

## References

- [https://github.com/cosmicstack-labs/mercury-agent/](https://github.com/cosmicstack-labs/mercury-agent/)
- [https://github.com/cosmicstack-labs/mercury-agent/issues/101](https://github.com/cosmicstack-labs/mercury-agent/issues/101)

## Related threats

- [cosmicstack-labs mercury-agent server-side request forgery in GitHub API handler](https://junglewise.ai/threats/cve-2026-90814-cosmicstack-labs-mercury-agent-server-side-request-forgery-in)
- [cosmicstack-labs mercury-agent shell command validation bypass](https://junglewise.ai/threats/cve-2026-90813-cosmicstack-labs-mercury-agent-shell-command-validation-bypass)
- [cosmicstack-labs mercury-agent privilege escalation in shell permission check](https://junglewise.ai/threats/cve-2026-90812-cosmicstack-labs-mercury-agent-privilege-escalation-in-shell)
- [Cosmicstack Labs Mercury Agent shell permission bypass via wc](https://junglewise.ai/threats/cve-2026-90811-cosmicstack-labs-mercury-agent-shell-permission-bypass-via-wc)