LLMHigh
CVE-2026-9353: A security vulnerability has been detected in NousResearch hermes-agent up to 2026.4.23. Impacted is…
- Occurred
- May 24, 2026
- Published
- May 24, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-9353
- cvss:HIGH
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: CVE describes a prompt injection vulnerability in an LLM agent framework allowing remote exploitation.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8