CVE-2026-14628: NousResearch hermes-agent path traversal in Live Webhook Endpoint

CVE-2026-14628 · Severity: medium · CVSS 5.3 · Published 2026-07-04

NousResearch hermes-agent is an AI agent framework that connects large language models to messaging platforms like Telegram and Discord. A security flaw in its media handling component allows an attacker to trick the AI into reading and sending sensitive files from the host server. While the attack is limited to certain file types (like .csv, .pdf, or .zip), it can be used to steal database exports, backups, or private documents by bypassing the agent's normal security boundaries.

Technologies: NousResearch Hermes Agent. Vendors: NousResearch.

Quick answers

Is CVE-2026-14628 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-14628 being exploited in the wild.
How severe is CVE-2026-14628?
Medium severity, with a CVSS score of 5.3, published 4 July 2026.
Which products and versions are affected?
NousResearch Hermes Agent up to 2026.5.16.
Is there a fix for CVE-2026-14628?
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-2026-14628 attacked?
It is attacked over the network, in a software library.
Am I affected by CVE-2026-14628?
Check whether you run NousResearch Hermes 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

A path traversal vulnerability exists in the `extract_media` function within `gateway/platforms/base.py`. The component uses a regular expression to identify `MEDIA:` tags in LLM responses but fails to perform directory containment or traversal checks on the resulting file paths. By using prompt injection, a remote attacker can force the agent to output a path like `MEDIA:/var/backups/data.zip`. The system then uses `os.path.expanduser()` and reads the file from the host filesystem to send as an attachment. While the exploit is restricted to files with specific extensions (e.g., .csv, .txt, .pdf, .zip, .docx), it bypasses the sandbox restrictions enforced in other modules like `file_tools.py`. As of the advisory date, the vendor has not responded to disclosure attempts.

Affected products

  • NousResearch hermes-agent up to 2026.5.16

Timeline

  • 2026-06-01: disclosed: Initial researcher report via GitHub Gist
  • 2026-07-04: advisory: CVE published and added to NVD/VulDB

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.