CVE-2026-9353

published 24 May 2026 · updated 26 May 2026

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

8.3HighCVSS 7.3EPSS 0%1 public exploits

A public exploit exists; no exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. No fixed version is recorded.

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

Vendors, products and packages with version ranges

VendorProductVersionsFixed
NousResearch=2026.4.0, =2026.4.1, =2026.4.10, =2026.4.11, =2026.4.12, =2026.4.13, =2026.4.14, =2026.4.15, =2026.4.16, =2026.4.17, =2026.4.18, =2026.4.19, =2026.4.2, =2026.4.20, =2026.4.21, =2026.4.22, =2026.4.23, =2026.4.3, =2026.4.4, =2026.4.5, =2026.4.6, =2026.4.7, =2026.4.8, =2026.4.9

Exploit evidence

1 public sources

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-9353 severity on Zeptric[![CVE-2026-9353](https://zeptric.io/badge/cve/CVE-2026-9353.svg)](https://zeptric.io/cve/CVE-2026-9353)