CVE-2026-9353 NousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection
Remote attackers can execute arbitrary code via injection in the Skills Guard component of the hermes-agent library.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-9353?
CVE-2026-9353 is a medium-severity code injection vulnerability in NousResearch hermes-agent, published on 24 May 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-9353?
3 open source packages ship an affected version, including hermes-agent.
| Package | Affected | Fixed in |
|---|---|---|
hermes-agent PyPI | All versions | 0.15.0 |
hermes-agent PyPI | All versions | 0.15.0 |
hermes-agent PyPI | All versions | 0.15.0 |
How do I fix CVE-2026-9353?
Upgrade hermes-agent to 0.15.0 or later.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-9353 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-9353 exists.
Sources
Also known as GHSA-238w-f66p-w349, PYSEC-2026-2509.