hermes-agent

Hermes Agent ☤ Hermes Agent | Hermes Desktop The self-improving AI agent built byNous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a...

path-traversal-CVE-2026-14628

Path Traversal Demo - Case Study : CVE-2026-14628 A minimal, runnable demonstration fo the Path TraversalCWE-22 vulnerability class, usicng the recently dislosed CVE-2026-14628 as a real-world reference point. The real vulnerability CVE-2026-14628 affects 'NousResearch/hermes-agent' 2026.5.16. Th...

CVE-2026-114463

The webhook platform gateway in Nous Research Hermes Agent versions builds the session chatid as webhook:routename:deliveryid and re-derives the authorizing route by splitting that string, so a route name containing a ":" resolves toolset authorization to a different, higher-privileged prefix rou...

EUVD-2026-107306

The webhook platform gateway in Nous Research Hermes Agent versions builds the session chatid as webhook:routename:deliveryid and re-derives the authorizing route by splitting that string, so a route name containing a ":" resolves toolset authorization to a different, higher-privileged prefix rou...

CVE-2026-114463 CVE-2026-114463

The webhook platform gateway in Nous Research Hermes Agent versions builds the session chatid as webhook:routename:deliveryid and re-derives the authorizing route by splitting that string, so a route name containing a ":" resolves toolset authorization to a different, higher-privileged prefix rou...

CVE-2026-114463 CVE-2026-114463

The webhook platform gateway in Nous Research Hermes Agent versions builds the session chatid as webhook:routename:deliveryid and re-derives the authorizing route by splitting that string, so a route name containing a ":" resolves toolset authorization to a different, higher-privileged prefix rou...

CVE-2026-114463

The webhook platform gateway in Nous Research Hermes Agent is vulnerable to an authorization bypass. The gateway constructs the session chat_id using the format webhook:{route_name}:{delivery_id} and re-derives the authorizing route by splitting this string. If a {route_name} contains a colon (:)...

PT-2026-120647

The webhook platform gateway in Nous Research Hermes Agent versions builds the session chat id as webhook:route name:delivery id and re-derives the authorizing route by splitting that string, so a route name containing a ":" resolves toolset authorization to a different, higher-privileged prefix...

CVE-2026-108593

9router 0.4.1 through 0.5.99 contains a configuration injection vulnerability in the POST /api/cli-tools/hermes-settings endpoint that allows authenticated dashboard users to inject arbitrary keys into the Hermes Agent config.yaml file. Attackers can submit a baseUrl containing double quotes and...

CVE-2026-108593 9router 0.4.1 through 0.5.99 Config Injection RCE via hermes-settings Endpoint

9router 0.4.1 through 0.5.99 contains a configuration injection vulnerability in the POST /api/cli-tools/hermes-settings endpoint that allows authenticated dashboard users to inject arbitrary keys into the Hermes Agent config.yaml file. Attackers can submit a baseUrl containing double quotes and...

EUVD-2026-96401

9router 0.4.1 through 0.5.99 contains a configuration injection vulnerability in the POST /api/cli-tools/hermes-settings endpoint that allows authenticated dashboard users to inject arbitrary keys into the Hermes Agent config.yaml file. Attackers can submit a baseUrl containing double quotes and...

CVE-2026-108593

The software 9router (versions 0.4.1 through 0.5.99 ) is vulnerable to a configuration injection vulnerability within the POST /api/cli-tools/hermes-settings endpoint. Authenticated dashboard users can exploit this by submitting a baseUrl containing double quotes and newlines, allowing them to in...

CVE-2026-108593: Improper Control of Generation of Code

9router 0.4.1 through 0.5.99 contains a configuration injection vulnerability in the POST /api/cli-tools/hermes-settings endpoint that allows authenticated dashboard users to inject arbitrary keys into the Hermes Agent config.yaml file. Attackers can submit a baseUrl containing double quotes and...

hermes-seagull

hermes-seagull !CIhttps://github.com/ly1123245599/hermes-...

Carbonato Botnet Compromises Docker Hosts to Deploy Telegram-Controlled Hermes AI Agent

Cybersecurity researchers have disclosed details of a new botnet malware called Carbonato that's targeting exposed Docker daemons to deploy an open-source artificial intelligence AI agent framework called Hermes Agent. "The implant installs the framework unchanged, then overwrites its SOUL.md...

Exploit for CVE-2026-71963

CVE-2026-71963 — Hermes Agent RCE via a repository-delivered...

hermes-agent v2026.9.11

Hermes Agent ☤ Hermes Agent | Hermes Desktop The self-improving AI agent built byNous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a...

CVE-2026-71963

Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user...

EUVD-2026-70526

Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user...

CVE-2026-71963 Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection

Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user...