NousResearch vulnerabilities and threats

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.

A security vulnerability has been detected in NousResearch hermes-agent up to 2026.4.30. Affected is the function GatewayStreamConsumer._filter_and_accumulate of the file gateway/stream_consumer.py of the component Streaming Reasoning Tag Filter. The manipulation leads to improper handling of case sensitivity. The attack may be initiated remotely. The attack's complexity is rated as high. The exploitability is told to be difficult. The exploit has been disclosed publicly and may be used. The project decided to not implement a dedicated fix: "[T]he analysis and the fix are both sound. It just lands below the bar for the maintenance cost of a duplicated scrub path."

Hermes Agent before 0.16.0 creates response_store.db and webhook_subscriptions.json with world-readable permissions (mode 0o644), exposing conversation history and HMAC secrets to local users. Attackers with local filesystem access can read these files directly to obtain sensitive data including conversation history, tool payloads, prompts, and per-route HMAC secrets.

Hermes Agent before 0.16.0 contains a DNS rebinding vulnerability in WebSocket endpoints that allows remote attackers to bypass Host and Origin validation. FastAPI HTTP middleware does not execute for WebSocket upgrade requests on /api/pty, /api/ws, /api/pub, and /api/events endpoints, enabling attackers to exploit DNS rebinding and inject malicious commands or read terminal output.

A vulnerability has been found in NousResearch hermes-agent up to 0.12.0. This affects the function resolve_session_by_title of the file hermes_state.py of the component resume Endpoint. Such manipulation of the argument Title leads to authorization bypass. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

A security flaw has been discovered in NousResearch hermes-agent up to 2026.4.23. This affects the function _sync_anthropic_entry_from_credentials_file of the file agent/credential_pool.py of the component Credential Pool Synchronization. The manipulation results in improper authentication. The attack must be initiated from a local position. 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.

A security vulnerability has been detected in NousResearch hermes-agent up to 2026.4.30. This vulnerability affects the function _handle_webhook_request of the file gateway/platforms/feishu.py of the component Webhook Endpoint. Such manipulation leads to resource consumption. The attack can be launched remotely. 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.

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function _scan_memory_content of the file tools/memory_tool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.

CVE-2026-10222 is a medium severity injection vulnerability in the NousResearch hermes-agent affecting versions 2026.4.0 through 2026.4.30. The flaw exists in the _sanitize_env_lines function within hermes_cli/config.py and can be exploited remotely. Exploitation requires a high level of complexity and is considered difficult. The vendor has not responded to the disclosure, and no official patch or remediation guidance is currently available. Public exploit code has been released.

A vulnerability was identified in NousResearch hermes-agent up to 0.12.0. Affected by this vulnerability is the function _compress_context of the file run_agent.py. The manipulation leads to injection. It is possible to initiate the attack remotely. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way.

A vulnerability was determined in NousResearch hermes-agent up to 2026.4.30. Affected is the function _serve_plugin_skill/skill_view of the file tools/skills_tool.py. Executing a manipulation can lead to injection. The attack may be performed from remote. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.

CVE-2026-9369 is a medium severity vulnerability in NousResearch hermes-agent version 2026.4.23. It involves an incorrect comparison in the _discover_dashboard_plugins function within the hermes_cli/web_server.py file. The flaw can be triggered by manipulating the HERMES_ENABLE_PROJECT_PLUGINS argument. Exploitation requires local access, and no vendor response or patch is currently available.

CVE-2026-9368 is a medium severity vulnerability in NousResearch hermes-agent up to version 2026.4.16. It affects the execute_code function in tools/code_execution_tool.py within the Environment Variable Handler component, leading to a sandbox issue. The vulnerability can be exploited remotely and a public exploit is available. The vendor has not responded to disclosure and no official fix or patch is currently known.

A vulnerability was determined in NousResearch hermes-agent up to 5157f5427f19488b31c6fdebbacd15d798ce7f63. This affects the function detect_dangerous_command of the file tools/approval.py of the component terminal_tool. This manipulation causes os command injection. It is possible to initiate the attack remotely. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.

CVE-2026-9366 is a medium severity injection vulnerability in the NousResearch hermes-agent version 2026.4.23. The issue exists in the _scan_context_content function within the agent/prompt_builder.py file. This vulnerability allows remote attackers to perform injection attacks. The exploit code has been publicly disclosed. The vendor has not responded or provided a fix at the time of this report.

A vulnerability was detected in NousResearch hermes-agent up to 2026.4.16. The affected element is an unknown function of the component Slack Agent/Mattermost Agent. The manipulation of the argument format_message results in escaping of output. The attack can be executed remotely. The exploit is now public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.

CVE-2026-9353 is a medium severity injection vulnerability in NousResearch hermes-agent versions 2026.4.0 through 2026.4.23. It affects an unknown function in the file agent/skills_guard.py related to the Skills Guard Multi-Word Prompt Handler component. The vulnerability arises from manipulation of the THREAT_PATTERNS argument, allowing injection. Remote exploitation is possible, and a public exploit has been disclosed. The vendor has not responded to the disclosure and no patch or remediation is currently available.

A weakness has been identified in NousResearch hermes-agent up to 2026.4.23. This issue affects the function _make_run_env of the file tools/environments/local.py of the component Messaging Gateway Handler. Executing a manipulation can lead to information disclosure. The attack may be launched remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.

A security flaw has been discovered in NousResearch hermes-agent up to 2026.4.16. This vulnerability affects the function _is_blocked_device of the file tools/file_tools.py of the component read_file Tool. Performing a manipulation results in path traversal. The attack may be initiated 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.

A vulnerability was identified in NousResearch hermes-agent up to 2026.4.16. This affects the function check_all_command_guards of the file tools/approval.py of the component Batch Runner. Such manipulation leads to missing authorization. The attack can be launched remotely. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way.