Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1110 CNY

100%

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

CVSS 7.3 · High EPSS 0.04% · P14

Possible ATT&CK Techniques 1AI

T1190 · Exploit Public-Facing Application

Affected Version Matrix 24

VendorProductVersion RangeStatus
NousResearchhermes-agent2026.4.0affected
2026.4.1affected
2026.4.2affected
2026.4.3affected
2026.4.4affected
2026.4.5affected
2026.4.6affected
2026.4.7affected
… +16 more rows
Get alerts for future matching vulnerabilitiesLog in to subscribe

I. Basic Information for CVE-2026-9353

Vulnerability Information

Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
NousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection
Source: NVD (National Vulnerability Database)
Vulnerability Description
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.
Source: NVD (National Vulnerability Database)
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
Source: NVD (National Vulnerability Database)
Vulnerability Type
输出中的特殊元素转义处理不恰当(注入)
Source: NVD (National Vulnerability Database)

Affected Products

VendorProductAffected VersionsCPESubscribe
NousResearchhermes-agent 2026.4.0 cpe:2.3:a:nousresearch:hermes-agent:*:*:*:*:*:*:*:*

II. Public POCs for CVE-2026-9353

#POC DescriptionSource LinkShenlong Link
AI-Generated POCPremium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-9353

登录查看更多情报信息。

Proof of Concept for CVE-2026-9353 (1)

News Coverage for CVE-2026-9353 (1)

Same Patch Batch · NousResearch · 2026-05-24 · 9 CVEs total

CVE-2026-93507.3 HIGHNousResearch hermes-agent Batch Runner approval.py check_all_command_guards authorization
CVE-2026-93667.3 HIGHNousResearch hermes-agent prompt_builder.py _scan_context_content injection
CVE-2026-93687.3 HIGHNousResearch hermes-agent Environment Variable code_execution_tool.py execute_code sandbox
CVE-2026-93677.3 HIGHNousResearch hermes-agent terminal_tool approval.py detect_dangerous_command os command in
CVE-2026-93516.5 MEDIUMNousResearch hermes-agent read_file Tool file_tools.py _is_blocked_device path traversal
CVE-2026-93546.5 MEDIUMNousResearch hermes-agent Slack Agent/Mattermost Agent escape output
CVE-2026-93525.3 MEDIUMNousResearch hermes-agent Messaging Gateway local.py _make_run_env information disclosure
CVE-2026-93695.3 MEDIUMNousResearch hermes-agent CLI web-dashboard web_server.py _discover_dashboard_plugins comp

IV. Related Vulnerabilities

V. Comments for CVE-2026-9353

No comments yet


Leave a comment