High Injection exploit reference

CVE-2026-9353 — NousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection

A security vulnerability has been detected in NousResearch hermes-agent up to 2026.4.23. Impacted is an unknown function of the file agent/skills_guard.py of the component Skills Guard Multi-Word Prompt Handler. The manipulation of the argument THREAT_PATTERNS leads to injection. Remote exploitation of the attack is possible. The exploit has been disclosed publicly and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

Published May 24, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulDB

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

EPSS 0.5% (30-day exploitation probability)+6
Technical severity (high)+6
CISA SSVC: exploitation "poc"+5
Automatable exploitation (SSVC)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

0.52%

ahead of 43% of scored CVEs · Oct 14, 2026

Affects

NousResearch

Hermes-agent

CVSS base

7.3

High · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

Proof of concept

none · proof-of-concept · active

Automatable

Yes

can an attacker script the kill-chain steps

Technical impact

Partial

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (NousResearch Hermes-agent).
The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
No fix documented in the sources: reduce exposure and monitor the vendor advisory.
Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
NousResearch	Hermes-agent	version 2026.4.12version 2026.4.23version 2026.4.22version 2026.4.21version 2026.4.20version 2026.4.19version 2026.4.18version 2026.4.17 and 16 more version 2026.4.16version 2026.4.15version 2026.4.14version 2026.4.13version 2026.4.0version 2026.4.11version 2026.4.10version 2026.4.9version 2026.4.8version 2026.4.7version 2026.4.6version 2026.4.5version 2026.4.4version 2026.4.3version 2026.4.2version 2026.4.1	Vulnerable	CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Network

Attack complexity

Low

Privileges required

None

User interaction

None

Scope

Unchanged

Confidentiality

Low

Integrity

Low

Availability

Low

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
6.9	CVSS 4.0	Medium	—	—	VulDB via CVE Program (cve.org) e CISA ADP
5.5	CVSS 4.0	Medium	—	—	cna@vuldb.com via NIST National Vulnerability Database
7.3	CVSS 3.1	High	3.9	3.4	cna@vuldb.com via NIST National Vulnerability Database
7.3	CVSS 3.1	High	—	—	VulDB via CVE Program (cve.org) e CISA ADP
7.3	CVSS 3.0	High	—	—	VulDB via CVE Program (cve.org) e CISA ADP
7.5	CVSS 2.0	High	10.0	6.4	cna@vuldb.com via NIST National Vulnerability Database
7.5	CVSS 2.0	High	—	—	VulDB via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L (score shown at the top: cna@vuldb.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-74 · Injection

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.52%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
Look for parameters with command/query metacharacters and unexpected child processes of the service.

web/proxy/WAF logsnetwork IDS/IPSapplication logsendpoint telemetry (EDR)

Timeline

What happened to this CVE, newest first.

2026
Affected products added · nousresearch/hermes-agent
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
SSVC assessment updated
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 13, 2026
CVSS changed · 7.3
Oct 13, 2026 · NIST National Vulnerability Database
Source status changed · → Deferred
Oct 13, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 13, 2026 · NIST National Vulnerability Database
CVE published
May 24, 2026 · VulDB

Source activity

Repeated readings are counted rather than listed.

1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

4 on the record

vuldb.com/submit/812216
third-party-advisory, NIST National Vulnerability Database
gist.github.com/YLChen-007/82a3539d6358842e69dfaef0a9fcf14a
exploit, NIST National Vulnerability Database
vuldb.com/vuln/365316
vdb-entry, technical-description, NIST National Vulnerability Database
vuldb.com/vuln/365316/cti
signature, permissions-required, NIST National Vulnerability Database

Elsewhere on this site

NousResearch
every CVE for this vendor

Injection
same class

CWE-74
other pages naming this weakness

Related CVEs (same products)

Medium CVE-2026-18993 NousResearch hermes-agent Memory Toolset model_tools.py access control Aug 6, 2026
Medium CVE-2026-18976 NousResearch hermes-agent disabled_toolsets agent_init.py get_tool_definitions privileges assignment Aug 5, 2026
Medium CVE-2026-18775 NousResearch hermes-agent Browser Tooling browser_tool.py browser_snapshot server-side request forgery Aug 4, 2026
Medium CVE-2026-18774 NousResearch hermes-agent xAI Image Generation Provider image_gen_provider.py save_url_image server-side request forgery Aug 4, 2026
Medium CVE-2026-18773 NousResearch hermes-agent Quick run.py _check_slash_access authorization Aug 4, 2026
Medium CVE-2026-17432 NousResearch hermes-agent SimpleX Gateway Authorization adapter.py access control Jul 25, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No fixed version, patch or mitigation documented.
No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-9353 is "NousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection", rated High. It affects Hermes-agent (NousResearch); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 7.3 describes technical severity. EPSS 0.52% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.