CVE-2026-18993: Improper Access Controls in NousResearch hermes-agent
A vulnerability exists in NousResearch hermes-agent up to version 0.16.0 in the Memory Toolset component, specifically in the hermes-agent/model_tools.py file. This issue involves improper access controls that can be exploited remotely. The vulnerability has a CVSS 3.1 score of 6.3, indicating a medium severity level. Exploit code for this vulnerability is publicly available, but there are no known exploits observed in the wild. No patch or official fix information is currently provided.
AI Analysis
Technical Summary
The vulnerability identified as CVE-2026-18993 affects NousResearch hermes-agent versions up to 0.16.0. It involves improper access controls in an unspecified functionality within the Memory Toolset component, located in the hermes-agent/model_tools.py file. The flaw allows remote attackers to manipulate access controls, potentially leading to limited confidentiality, integrity, and availability impacts. The CVSS vector indicates low attack complexity, requires low privileges, no user interaction, and affects confidentiality, integrity, and availability to a low degree. Exploit code is publicly available, but no active exploitation has been reported.
Potential Impact
The vulnerability allows remote attackers with low privileges to bypass proper access controls, potentially resulting in limited unauthorized access or modification of data and limited disruption of service. The impact is rated as low to medium severity based on the CVSS score of 6.3, reflecting limited confidentiality, integrity, and availability impacts.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or patch information is currently available. Until a patch is released, restrict access to the affected component where possible and monitor for any suspicious activity related to this vulnerability.
CVE-2026-18993: Improper Access Controls in NousResearch hermes-agent
Description
A vulnerability exists in NousResearch hermes-agent up to version 0.16.0 in the Memory Toolset component, specifically in the hermes-agent/model_tools.py file. This issue involves improper access controls that can be exploited remotely. The vulnerability has a CVSS 3.1 score of 6.3, indicating a medium severity level. Exploit code for this vulnerability is publicly available, but there are no known exploits observed in the wild. No patch or official fix information is currently provided.
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.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability identified as CVE-2026-18993 affects NousResearch hermes-agent versions up to 0.16.0. It involves improper access controls in an unspecified functionality within the Memory Toolset component, located in the hermes-agent/model_tools.py file. The flaw allows remote attackers to manipulate access controls, potentially leading to limited confidentiality, integrity, and availability impacts. The CVSS vector indicates low attack complexity, requires low privileges, no user interaction, and affects confidentiality, integrity, and availability to a low degree. Exploit code is publicly available, but no active exploitation has been reported.
Potential Impact
The vulnerability allows remote attackers with low privileges to bypass proper access controls, potentially resulting in limited unauthorized access or modification of data and limited disruption of service. The impact is rated as low to medium severity based on the CVSS score of 6.3, reflecting limited confidentiality, integrity, and availability impacts.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or patch information is currently available. Until a patch is released, restrict access to the affected component where possible and monitor for any suspicious activity related to this vulnerability.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-4992-66px-gwh3
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-18993"]
- Ecosystems
- []
- Database Specific Severity
- LOW
- Cvss Version
- 3.1
Threat ID: 6a74cfaabf8831d5391b1668
Added to database: 08/06/2026, 18:17:14 UTC
Last enriched: 08/06/2026, 19:17:33 UTC
Last updated: 08/07/2026, 03:40:59 UTC
Views: 2
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.