CVE-2026-71963
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.
Faiblesse
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.
Références
- https://github.com/NousResearch/hermes-agent/commit/f6234d00c5d59450adea1d7edd30ad3859375c79
- https://github.com/NousResearch/hermes-agent/pull/101483
- https://www.manifold.security/blog/ai-coding-agents-git-hijack
- https://www.vulncheck.com/advisories/hermes-agent-rce-via-git-core-fsmonitor-config-injection
Trouvez la faille avant un attaquant.
Connectez-vous avec GitHub et lancez votre premier audit en moins d'une minute. L'offre gratuite ne nécessite aucune carte bancaire.