---
title: "CVE-2026-71963: Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection"
url: https://erroneo.us/security/cve/CVE-2026-71963/
description: "CVE-2026-71963 (NousResearch hermes-agent): Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-09-03
date_modified: 2026-10-21
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-71963"
kev: false
cvss: 8.6
epss: 0.00858
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-71963: Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection

**Signal:** Normal patch cycle. No exploitation signal; fix it in your next routine update if you are affected. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.9% , percentile 58: FIRST’s model estimates a 0.9% chance of exploitation activity in the next 30 days, higher than 58% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Editorial verdict: Patch this week. GitSpawn: Repo Git Config Runs Code in AI Coding Agents — Update your coding agents this week and never point one at a repository that arrived as files until you have read its .git/config; ordinary clones are not affected, and no attacks have been reported.

## What it is

Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user opens the malicious repository and sends any message, the agent triggers a git status index refresh which executes the injected command in the user's process context, exposing the full environment including configured provider API keys.

## Affected products (CVE record)

- NousResearch hermes-agent: 0.18.2 <= 0.21.0

## Severity

- VulnCheck CVSS 4.0: 8.6 `CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`
- VulnCheck CVSS 3.1: 8.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable no , technical impact total .
- FIRST EPSS (model of 2026-10-21): 0.86% probability of exploitation activity in the next 30 days; percentile 58.

## Sources

- [Patch Commit](https://github.com/NousResearch/hermes-agent/commit/f6234d00c5d59450adea1d7edd30ad3859375c79)
- [CVE.org record CVE-2026-71963](https://www.cve.org/CVERecord?id=CVE-2026-71963)
- [NVD entry CVE-2026-71963](https://nvd.nist.gov/vuln/detail/CVE-2026-71963)
- [Manifold Blog](https://www.manifold.security/blog/ai-coding-agents-git-hijack)
- [Pull Request](https://github.com/NousResearch/hermes-agent/pull/101483)
- [vulncheck.com](https://www.vulncheck.com/advisories/hermes-agent-rce-via-git-core-fsmonitor-config-injection)

---
Source page: https://erroneo.us/security/cve/CVE-2026-71963/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt