CVE-2026-18976
Received Received - Intake

Incorrect Privilege Assignment in Hermes-Agent

Vulnerability report for CVE-2026-18976, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-08-06

Last updated on: 2026-08-06

Assigner: VulDB

Description

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function get_tool_definitions of the file agent/agent_init.py of the component disabled_toolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The exploit has been publicly disclosed and may be utilized. The project was informed of the problem early through an issue report.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-06
Last Modified
2026-08-06
Generated
2026-08-06
AI Q&A
2026-08-06
EPSS Evaluated
N/A
NVD
EUVD

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
nousresearch hermes-agent to 0.16.0 (inc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-266 A product incorrectly assigns a privilege to a particular actor, creating an unintended sphere of control for that actor.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

CVE-2026-18976 is a vulnerability in NousResearch's hermes-agent up to version 0.16.0. It involves incorrect privilege assignment in the get_tool_definitions function of agent/agent_init.py. The flaw allows memory provider tools like fact_store and fact_feedback to be re-injected into the tool surface even when explicitly disabled via the disabled_toolsets parameter. The issue occurs because the guard condition only checks enabled_toolsets and ignores disabled_toolsets, bypassing intended restrictions.

Detection Guidance

Check Hermes Agent logs for unauthorized tool injections or memory provider tool usage. Inspect agent/agent_init.py for the disabled_toolsets bypass condition where tools are re-added despite being disabled. Verify if fact_store or fact_feedback tools are active when disabled_toolsets=['memory'] is set.

Impact Analysis

This vulnerability allows unauthorized access to memory provider tools even when they are meant to be disabled. Attackers could exploit this to perform unauthorized memory writes, updates, or searches. This could lead to unintended persistence of sensitive data or broken security assumptions in workflows, potentially compromising data integrity and confidentiality.

Compliance Impact

This vulnerability could impact compliance with GDPR and HIPAA by enabling unauthorized access to sensitive data. GDPR requires strict data protection and user consent, while HIPAA mandates safeguards for protected health information. Unauthorized memory access could lead to data breaches, violating these regulations and resulting in legal penalties or loss of trust.

Mitigation Strategies

Upgrade Hermes Agent to the latest version where the disabled_toolsets check is enforced. Review tool configurations to ensure disabled_toolsets=['memory'] is properly applied. Monitor for unauthorized memory tool usage in logs.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-18976. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart