PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-14626 NousResearch CVE debrief

CVE-2026-14626 is a weakness in the NousResearch hermes-agent up to version 2026.4.30. Specifically, the AIAgent.run_conversation function in the run_agent.py file of the HTTP API component is vulnerable to manipulation of the 'todos' argument, leading to a denial of service (DoS) condition. The vulnerability has a CVSS score of 2.1, indicating a low severity. The attack can be initiated remotely, and public exploit availability could facilitate attacks. However, the vendor, NousResearch, did not respond to early disclosure. As of the CVE publication date of 2026-07-04, there is limited information available on affected products or versions. Further investigation and defensive actions are necessary to address this vulnerability.

Vendor
NousResearch
Product
hermes-agent
CVSS
LOW 2.1
CISA KEV
Not listed in stored evidence
Original CVE published
2026-07-04
Original CVE updated
2026-07-04
Advisory published
2026-07-04
Advisory updated
2026-07-04

Who should care

Security teams responsible for NousResearch hermes-agent deployments should prioritize assessment and mitigation of CVE-2026-14626. Given the low CVSS score, this vulnerability may not be a critical priority but still requires attention due to potential remote exploitation and public exploit availability. Organizations using affected versions of NousResearch hermes-agent should review their inventory and apply patches or mitigations as they become available.

Technical summary

CVE-2026-14626 affects NousResearch hermes-agent up to version 2026.4.30, specifically in the AIAgent.run_conversation function of the run_agent.py file within the HTTP API component. The vulnerability allows for remote denial of service (DoS) attacks through manipulation of the 'todos' argument. The CVSS:4.0 vector is AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X, indicating a low severity score of 2.1. The weakness is categorized under CWE-404. Public exploit availability and remote attack complexity increase the urgency for affected organizations to assess and mitigate this vulnerability.

Defensive priority

CVE-2026-14626 has a low CVSS score of 2.1, but its remote exploitability and public exploit availability suggest a moderate priority for defensive actions. Security teams should focus on inventory checks, patch management, and potential compensating controls for NousResearch hermes-agent deployments.

Recommended defensive actions

  • Assess NousResearch hermes-agent deployments to identify affected versions (up to 2026.4.30).
  • Monitor for and apply patches or updates from NousResearch as they become available.
  • Implement network and API protections to detect and prevent exploitation attempts.
  • Review and enhance logging and monitoring for suspicious activity related to the HTTP API.
  • Consider compensating controls if patches are not immediately feasible.

Evidence notes

The CVE and NVD records provide initial details on CVE-2026-14626. However, limited information is available on affected products, versions, or user bases. The vendor, NousResearch, did not respond to early disclosure. Further investigation is needed to determine the full scope of impacted systems and to verify vendor remediation plans.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-14626 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-14626

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-14626 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-14626

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.