CVE-2026-14626: Denial of Service in NousResearch hermes-agent
A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. The impacted element is the function AIAgent.run_conversation of the file run_agent.py of the component HTTP API. This manipulation of the argument todos causes denial of service. The attack can be initiated remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.
AI Analysis
Technical Summary
This vulnerability affects the NousResearch hermes-agent product up to version 2026.4.30. It is caused by improper handling of the 'todos' argument in the AIAgent.run_conversation function within the run_agent.py file of the HTTP API component. An attacker can remotely manipulate this argument to trigger a denial of service condition, disrupting the normal operation of the agent. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity. Although the exploit code has been publicly disclosed, there is no known exploit in the wild and no vendor response or patch has been provided as of the publication date.
Potential Impact
Successful exploitation results in denial of service of the hermes-agent, potentially causing service disruption. The attack can be performed remotely without requiring user interaction or elevated privileges, which increases the risk of availability impact. There is no indication of confidentiality or integrity impact.
Mitigation Recommendations
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 limiting network exposure of the hermes-agent HTTP API to trusted sources to reduce risk.
CVE-2026-14626: Denial of Service in NousResearch hermes-agent
Description
A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. The impacted element is the function AIAgent.run_conversation of the file run_agent.py of the component HTTP API. This manipulation of the argument todos causes denial of service. The attack can be initiated remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.
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
This vulnerability affects the NousResearch hermes-agent product up to version 2026.4.30. It is caused by improper handling of the 'todos' argument in the AIAgent.run_conversation function within the run_agent.py file of the HTTP API component. An attacker can remotely manipulate this argument to trigger a denial of service condition, disrupting the normal operation of the agent. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity. Although the exploit code has been publicly disclosed, there is no known exploit in the wild and no vendor response or patch has been provided as of the publication date.
Potential Impact
Successful exploitation results in denial of service of the hermes-agent, potentially causing service disruption. The attack can be performed remotely without requiring user interaction or elevated privileges, which increases the risk of availability impact. There is no indication of confidentiality or integrity impact.
Mitigation Recommendations
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 limiting network exposure of the hermes-agent HTTP API to trusted sources to reduce risk.
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: 07/12/2026, 08:44:51 UTC
Last updated: 08/18/2026, 10:54:22 UTC
Views: 72
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.