# CVE-2026-108769: zhayujie CowAgent denial of service in Markdown rendering

Source: https://junglewise.ai/threats/cve-2026-108769-a-security-flaw-has-been-discovered-in-zhayujie-cowagent-up-to-2  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-11. Updated: 2026-10-16  
License: CC BY 4.0 with a link back

CVE-2026-108769 · Severity: medium · CVSS 4.3 · Published 2026-10-11

CowAgent is a desktop and web-based AI agent that streams responses from language models to users. A flaw in how streamed answers are rendered as Markdown causes the UI to repeatedly reparse the entire accumulated response on each update, allowing a model to craft oversized responses that exhaust CPU and memory resources and freeze or crash the interface.

Technologies: [Zhayujie CowAgent](https://junglewise.ai/threats/technologies/cowagent). Vendors: [Zhayujie](https://junglewise.ai/threats/vendors/zhayujie).

## Quick answers

**Is CVE-2026-108769 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-108769 being exploited in the wild.

**How severe is CVE-2026-108769?** Medium severity, with a CVSS score of 4.3, published 11 October 2026.

**Which products and versions are affected?** Zhayujie CowAgent up to 2.2.0.

**Is there a fix for CVE-2026-108769?** 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-2026-108769 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-108769?** Check whether you run Zhayujie CowAgent 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 uncontrolled resource consumption flaw (CWE-400) in the Markdown rendering pipeline. Streamed model output is reparsed in full on every delta update without a content size cap on ordinary answers, unlike the capped reasoning output (4 KB). An attacker-controlled or compromised model can emit a large Markdown response, causing 81x amplification in cumulative parsing work and stalling both the web console and desktop UI.

## Affected products

- zhayujie CowAgent up to 2.2.0

## Timeline

- 2026-10-11: disclosed

## References

- [https://github.com/outlookgp/CVE/tree/main/CowAgent_Markdown_Stream_Render_DoS_Report](https://github.com/outlookgp/CVE/tree/main/CowAgent_Markdown_Stream_Render_DoS_Report)
- [https://vuldb.com/cve/CVE-2026-108769](https://vuldb.com/cve/CVE-2026-108769)

## Related threats

- [zhayujie CowAgent resource exhaustion in tool-call argument parsing](https://junglewise.ai/threats/cve-2026-108768-a-vulnerability-was-identified-in-zhayujie-cowagent-up-to-2-2-0)
- [zhayujie CowAgent uncontrolled memory allocation in media download](https://junglewise.ai/threats/cve-2026-108683-a-security-vulnerability-has-been-detected-in-zhayujie-cowagent)
- [zhayujie CowAgent denial of service in /upload endpoint](https://junglewise.ai/threats/cve-2026-108682-a-weakness-has-been-identified-in-zhayujie-cowagent-up-to-2-1-6)
- [zhayujie CowAgent denial of service in Web Console](https://junglewise.ai/threats/cve-2026-108681-a-security-flaw-has-been-discovered-in-zhayujie-cowagent-up-to-2)
- [zhayujie CowAgent denial of service in Bash tool](https://junglewise.ai/threats/cve-2026-84427-zhayujie-cowagent-denial-of-service-in-bash-tool)