Is there a public PoC exploit available for CVE-2026-14625?

Yes, a public proof-of-concept exploit is available for CVE-2026-14625. Prioritise patching immediately. EPSS: 0.2%.

hermes-agent CVE-2026-14625

Q: What is the CVSS score of CVE-2026-14625?

CVE-2026-14625 has a CVSS 4.0 base score of 2.1 (Low). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/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. EPSS exploitation probability: 0.2%.

EUVD-2026-41664 LOW

Protection Mechanism Failure (CWE-693)

2026-07-04 VulDB

GHSA-5p65-6hm5-c89p

Information Disclosure Hermes Agent Nousresearch

2.1

CVSS 4.0 · Vendor: VulDB

Severity by source

Vendor (VulDB) PRIMARY

2.1 MEDIUM

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/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

vuln.today AI

6.3 MEDIUM

Network-accessible shell.exec bypass requires low-privilege authentication; no scope change, and impact is bounded to low C/I/A on the vulnerable system only.

3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L

4.0 AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N

Primary rating from Vendor (VulDB).

CVSS VectorVendor: VulDB

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Lifecycle Timeline

Severity Changed

Jul 04, 2026 - 12:22 NVD

MEDIUM LOW

CVSS changed

Jul 04, 2026 - 12:22 NVD

5.3 (MEDIUM) 2.1 (LOW)

Analysis Generated

Jul 04, 2026 - 12:21 vuln.today

DescriptionCVE.org

A security flaw has been discovered in NousResearch hermes-agent up to 0.15.2. The affected element is the function shell.exec of the file tui_gateway/server.py. The manipulation results in protection mechanism failure. It is possible to launch the attack remotely. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.

AnalysisAI

Protection mechanism failure in NousResearch hermes-agent (≤ 0.15.2) allows remote authenticated attackers to bypass shell execution controls via the shell.exec function in tui_gateway/server.py, resulting in low-level confidentiality, integrity, and availability impact. The vulnerability is classified under CWE-693 and carries a CVSS 4.0 score of 5.3 (Medium), with a publicly available proof-of-concept exploit hosted on GitHub. No patch has been issued - the vendor did not respond to the researcher's disclosure - meaning all deployments of hermes-agent up to and including version 0.15.2 remain exposed.

Technical ContextAI

hermes-agent is a TUI (terminal user interface) gateway application developed by NousResearch, an AI research organization. The affected component is the shell.exec function within tui_gateway/server.py, which is responsible for executing shell commands as part of the gateway's interface. CWE-693 (Protection Mechanism Failure) indicates that a security control - likely input validation, sandboxing, or command allowlisting intended to restrict which shell commands can be invoked - is either incorrectly implemented or can be circumvented by a sufficiently crafted request. The CVSS 4.0 vector (AV:N/AC:L/AT:N/PR:L/UI:N) confirms the vulnerability is network-reachable, requires no special attack target conditions, and demands only low-privilege credentials, making it straightforward to exploit once access is obtained. The CPE string cpe:2.3:a:nousresearch:hermes-agent:*:*:*:*:*:*:*:* confirms all sub-versions through 0.15.2 are in scope.

RemediationAI

No vendor-released patch has been identified at time of analysis - the vendor did not respond to responsible disclosure. Until a fix is issued, administrators should restrict network access to the hermes-agent TUI gateway using host-based or network-layer firewall rules, limiting exposure to trusted, explicitly enumerated IP addresses only (note: this does not eliminate risk for authorized users who might abuse the flaw). If shell execution via the gateway is not operationally required, disabling or removing the shell.exec code path in tui_gateway/server.py is the most effective compensating control, though this requires code modification and may break intended functionality. Organizations should monitor VulDB advisory https://vuldb.com/vuln/376141 and the CVE record at https://vuldb.com/cve/CVE-2026-14625 for any vendor patch announcement. Downgrading or halting use of hermes-agent in production environments with untrusted low-privileged users is advisable given the live public exploit.