CVE-2026-14626: Denial of Service in NousResearch hermes-agent
A denial of service vulnerability exists in NousResearch hermes-agent versions 2026.4.0 through 2026.4.30. The issue is in the AIAgent.run_conversation function within the HTTP API component, where manipulation of the 'todos' argument can cause the service to become unavailable. The vulnerability can be exploited remotely without user interaction or elevated privileges. No official fix or patch has been announced by the vendor, who has not responded to disclosure attempts. The CVSS 4.0 base score is 5.3, indicating a medium severity level.
AI Analysis
Technical Summary
CVE-2026-14626 is a medium severity denial of service vulnerability affecting NousResearch hermes-agent up to version 2026.4.30. The vulnerability arises from improper handling of the 'todos' argument in the AIAgent.run_conversation function of the run_agent.py file, part of the HTTP API component. An attacker can remotely trigger this flaw to cause a denial of service condition. Although the exploit code has been publicly disclosed, there is no indication of known exploitation in the wild. The vendor has not provided any response or patch at the time of this report.
Potential Impact
Successful exploitation results in denial of service, causing the affected hermes-agent service to become unavailable. This can disrupt operations relying on the agent's HTTP API. There is no indication of privilege escalation, data disclosure, or code execution associated with this vulnerability.
Mitigation Recommendations
No official patch or remediation has been announced by the vendor. Since the vendor has not responded to disclosure and no fixes are available, users should consider implementing network-level protections such as restricting access to the hermes-agent HTTP API to trusted sources only. Monitor for unusual activity targeting the 'todos' argument. Stay alert for any future vendor advisories or patches addressing this issue.
CVE-2026-14626: Denial of Service in NousResearch hermes-agent
Description
A denial of service vulnerability exists in NousResearch hermes-agent versions 2026.4.0 through 2026.4.30. The issue is in the AIAgent.run_conversation function within the HTTP API component, where manipulation of the 'todos' argument can cause the service to become unavailable. The vulnerability can be exploited remotely without user interaction or elevated privileges. No official fix or patch has been announced by the vendor, who has not responded to disclosure attempts. The CVSS 4.0 base score is 5.3, indicating a medium severity level.
CVSS v4.0
Score 5.3medium
Affected software
pkg:pypi/hermes-agentcpe:2.3:a:nousresearch:hermes-agent:*:*:*:*:*:*:*:*Run 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
CVE-2026-14626 is a medium severity denial of service vulnerability affecting NousResearch hermes-agent up to version 2026.4.30. The vulnerability arises from improper handling of the 'todos' argument in the AIAgent.run_conversation function of the run_agent.py file, part of the HTTP API component. An attacker can remotely trigger this flaw to cause a denial of service condition. Although the exploit code has been publicly disclosed, there is no indication of known exploitation in the wild. The vendor has not provided any response or patch at the time of this report.
Potential Impact
Successful exploitation results in denial of service, causing the affected hermes-agent service to become unavailable. This can disrupt operations relying on the agent's HTTP API. There is no indication of privilege escalation, data disclosure, or code execution associated with this vulnerability.
Mitigation Recommendations
No official patch or remediation has been announced by the vendor. Since the vendor has not responded to disclosure and no fixes are available, users should consider implementing network-level protections such as restricting access to the hermes-agent HTTP API to trusted sources only. Monitor for unusual activity targeting the 'todos' argument. Stay alert for any future vendor advisories or patches addressing this issue.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-07-03T17:07:48.069Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a48fae127e9c79719249b46
Added to database: 07/04/2026, 12:21:53 UTC
Last enriched: 07/04/2026, 12:36:27 UTC
Last updated: 07/04/2026, 13:17:47 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.