Injection Vulnerability in NousResearch hermes-agent Skills Guard Multi-Word Prompt Handler
CVE-2026-9353

6.9MEDIUM

Key Information:

Vendor

Nousresearch

Status
Hermes-agent
Vendor
CVE Published:
24 May 2026

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-9353?

A security vulnerability has been identified in the NousResearch hermes-agent affecting the Skills Guard Multi-Word Prompt Handler. The vulnerability stems from improper handling of the THREAT_PATTERNS argument in the agent/skills_guard.py file, which opens the door for potential injection attacks. These attacks can be exploited remotely, posing a significant risk to systems utilizing this software. Despite the early notification of the vendor regarding this issue, no response has been documented. This lack of communication emphasizes the urgency for users to be aware of their systems' security posture.

Affected Version(s)

hermes-agent 2026.4.0

hermes-agent 2026.4.1

hermes-agent 2026.4.2

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2026-9353 - Proof of Concept

References

https://vuldb.com/vuln/365316
vdb-entrytechnical-description
https://vuldb.com/vuln/365316/cti
signaturepermissions-required
https://vuldb.com/submit/812216
third-party-advisory

CVSS V4

Score:
6.9
Severity:
MEDIUM
Confidentiality:
Low
Integrity:
Low
Availability:
Low
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

Eric-i (VulDB User)
VulDB CNA Team
.