CVE-2026-10221: Injection in NousResearch hermes-agent
CVE-2026-10221 is a medium-severity injection vulnerability in the NousResearch hermes-agent up to version 0. 12. 0. The issue exists in the _compress_context function within run_agent. py and can be exploited remotely without authentication. Although an exploit is publicly available, there is no vendor response or official patch at this time. The vulnerability allows injection attacks that may impact confidentiality, integrity, and availability to a limited extent.
AI Analysis
Technical Summary
This vulnerability affects the NousResearch hermes-agent versions 0.1 through 0.12.0 in the _compress_context function of run_agent.py. It allows remote attackers to perform injection attacks due to improper input handling. The CVSS 4.0 base score is 6.9, indicating a medium severity with network attack vector, no privileges or user interaction required, and partial impact on confidentiality, integrity, and availability. The vendor has not provided any advisory or patch, and no official remediation level is assigned.
Potential Impact
Successful exploitation can lead to injection attacks that may partially compromise confidentiality, integrity, and availability of the affected system. The vulnerability can be triggered remotely without authentication or user interaction. However, the impact is limited as indicated by the CVSS vector. There are no known exploits in the wild beyond the publicly available proof-of-concept.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded or released a fix, users should monitor official channels for updates. Until a patch is available, consider restricting network access to the hermes-agent service and applying any available application-level input validation or filtering as a temporary mitigation.
CVE-2026-10221: Injection in NousResearch hermes-agent
Description
CVE-2026-10221 is a medium-severity injection vulnerability in the NousResearch hermes-agent up to version 0. 12. 0. The issue exists in the _compress_context function within run_agent. py and can be exploited remotely without authentication. Although an exploit is publicly available, there is no vendor response or official patch at this time. The vulnerability allows injection attacks that may impact confidentiality, integrity, and availability to a limited extent.
CVSS v4.0
Score 6.9medium
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability affects the NousResearch hermes-agent versions 0.1 through 0.12.0 in the _compress_context function of run_agent.py. It allows remote attackers to perform injection attacks due to improper input handling. The CVSS 4.0 base score is 6.9, indicating a medium severity with network attack vector, no privileges or user interaction required, and partial impact on confidentiality, integrity, and availability. The vendor has not provided any advisory or patch, and no official remediation level is assigned.
Potential Impact
Successful exploitation can lead to injection attacks that may partially compromise confidentiality, integrity, and availability of the affected system. The vulnerability can be triggered remotely without authentication or user interaction. However, the impact is limited as indicated by the CVSS vector. There are no known exploits in the wild beyond the publicly available proof-of-concept.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded or released a fix, users should monitor official channels for updates. Until a patch is available, consider restricting network access to the hermes-agent service and applying any available application-level input validation or filtering as a temporary mitigation.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-05-31T07:51:23.739Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a1de30ee29bf47b503a5825
Added to database: 6/1/2026, 7:52:46 PM
Last enriched: 6/1/2026, 8:04:23 PM
Last updated: 6/2/2026, 7:25:46 AM
Views: 9
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.