CVE-2026-9353: hermes-agent has an Injection issue
(updated )
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.
References
- gist.github.com/YLChen-007/82a3539d6358842e69dfaef0a9fcf14a
- github.com/NousResearch/hermes-agent/commit/7ebebfbb8d10937cbf2219b4cf5e121b71e67428
- github.com/NousResearch/hermes-agent/pull/26852
- github.com/advisories/GHSA-238w-f66p-w349
- nvd.nist.gov/vuln/detail/CVE-2026-9353
- vuldb.com/submit/812216
- vuldb.com/vuln/365316
- vuldb.com/vuln/365316/cti
Code Behaviors & Features
Detect and mitigate CVE-2026-9353 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →