This vulnerability in NousResearch hermes-agent affects the Slack Agent/Mattermost Agent component's handling of the format_message argument, leading to improper escaping of output. The issue allows remote attackers to manipulate output formatting, potentially causing unintended behavior. The vulnerability is present in all versions up to 2026.4.16. The CVSS 4.0 vector indicates network attack vector, low attack complexity, no privileges or user interaction required, and limited impact on confidentiality and availability. No official patch or remediation guidance has been provided by the vendor, who has not responded to the disclosure.

The vulnerability allows remote attackers to manipulate output escaping in the affected component, which could lead to unintended information disclosure or other output-related issues. The CVSS score of 6.9 reflects a medium severity with limited impact on confidentiality and availability. There is no evidence of active exploitation in the wild at this time.

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded and no official fix is available, users should monitor for updates from NousResearch. Until a patch is released, consider restricting network access to the hermes-agent service or applying compensating controls to limit exposure to untrusted inputs in the Slack Agent/Mattermost Agent component.