CVE-2026-18976: Incorrect Privilege Assignment in NousResearch hermes-agent
A vulnerability in NousResearch hermes-agent up to version 0.16.0 allows remote attackers to cause incorrect privilege assignment via the get_tool_definitions function in agent/agent_init.py. This issue relates to improper handling in the disabled_toolsets Handler component. The vulnerability has a CVSS score of 6.3 and has been publicly disclosed, but no known exploits are currently observed in the wild.
AI Analysis
Technical Summary
The vulnerability identified as CVE-2026-18976 affects NousResearch hermes-agent versions up to 0.16.0. It involves the get_tool_definitions function within the agent/agent_init.py file, specifically in the disabled_toolsets Handler component. This flaw leads to incorrect privilege assignment, potentially allowing an attacker with network access and low privileges to escalate their privileges without user interaction. The vulnerability has been publicly disclosed, and the project was notified early via an issue report. The CVSS v3.1 base score is 6.3, reflecting a network attack vector with low attack complexity, requiring low privileges, no user interaction, and impacts on confidentiality, integrity, and availability at a low level.
Potential Impact
The vulnerability allows an attacker to manipulate privilege assignments incorrectly, potentially leading to unauthorized access or actions within the affected system. The impact is rated as low severity, with limited confidentiality, integrity, and availability impacts. No active exploitation in the wild has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no patch or official fix information is provided, users should monitor vendor communications for updates. Until a fix is available, limit network exposure of the affected component and restrict privileges where possible to reduce risk.
CVE-2026-18976: Incorrect Privilege Assignment in NousResearch hermes-agent
Description
A vulnerability in NousResearch hermes-agent up to version 0.16.0 allows remote attackers to cause incorrect privilege assignment via the get_tool_definitions function in agent/agent_init.py. This issue relates to improper handling in the disabled_toolsets Handler component. The vulnerability has a CVSS score of 6.3 and has been publicly disclosed, but no known exploits are currently observed in the wild.
CVSS v4.0
Score 5.3medium
Affected software
pkg:github/nousresearch/hermes-agentRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability identified as CVE-2026-18976 affects NousResearch hermes-agent versions up to 0.16.0. It involves the get_tool_definitions function within the agent/agent_init.py file, specifically in the disabled_toolsets Handler component. This flaw leads to incorrect privilege assignment, potentially allowing an attacker with network access and low privileges to escalate their privileges without user interaction. The vulnerability has been publicly disclosed, and the project was notified early via an issue report. The CVSS v3.1 base score is 6.3, reflecting a network attack vector with low attack complexity, requiring low privileges, no user interaction, and impacts on confidentiality, integrity, and availability at a low level.
Potential Impact
The vulnerability allows an attacker to manipulate privilege assignments incorrectly, potentially leading to unauthorized access or actions within the affected system. The impact is rated as low severity, with limited confidentiality, integrity, and availability impacts. No active exploitation in the wild has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no patch or official fix information is provided, users should monitor vendor communications for updates. Until a fix is available, limit network exposure of the affected component and restrict privileges where possible to reduce risk.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-6rr9-mpp7-j4mp
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-18976"]
- Ecosystems
- []
- Database Specific Severity
- LOW
- Cvss Version
- 3.1
Threat ID: 6a74cfabbf8831d5391b1fc6
Added to database: 08/06/2026, 18:17:15 UTC
Last enriched: 08/06/2026, 19:19:18 UTC
Last updated: 08/07/2026, 03:40:59 UTC
Views: 3
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.