Back

MEDIUM

NousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection

Published May 24, 2026

Description

A security vulnerability has been detected in NousResearch hermes-agent up to 2026.4.23. Impacted is an unknown function of the file agent/skills_guard.py of the component Skills Guard Multi-Word Prompt Handler. The manipulation of the argument THREAT_PATTERNS leads to injection. Remote exploitation of the attack is possible. The exploit has been disclosed publicly and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

Affected products

Remediation

No remediation recorded yet.

Weaknesses (2)

References (9)

Change history (0)

No recorded changes yet.

Sources
CVE.org / MITRE
Status PUBLISHED
Assigner VulDB
Published May 24, 2026
Updated May 26, 2026
Reserved May 23, 2026
CISA Vulnrichment
Updated May 26, 2026
NVD
Status Deferred
Modified Jul 23, 2026
Red Hat
Severity n/a
Public date n/a
ENISA EUVD
Assigner VulDB
Published May 24, 2026
Updated May 26, 2026
Exploited since n/a
EUVD-2026-31567 GHSA-238W-F66P-W349