# CVE-2026-9353: NousResearch hermes-agent prompt injection bypass in Skills Guard

Source: https://junglewise.ai/threats/cve-2026-9353-nousresearch-hermes-agent-prompt-injection-bypass-in-skills-guard  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-05-24. Updated: 2026-06-30  
License: CC BY 4.0 with a link back

CVE-2026-9353 · Severity: high · CVSS 7.3 · Published 2026-05-24

NousResearch hermes-agent is a tool used for managing AI agent skills and behaviors. A vulnerability in its security filtering component allows attackers to bypass safety checks by slightly modifying malicious commands, such as inserting extra words into a prompt. This could allow an attacker to install malicious skills that override the agent's core instructions, potentially leading to unauthorized actions or data manipulation without the user's knowledge.

Technologies: [NousResearch Hermes Agent](https://junglewise.ai/threats/technologies/hermes-agent), [hermes-agent (PyPI)](https://junglewise.ai/threats/technologies/pypi-hermes-agent). Vendors: [NousResearch](https://junglewise.ai/threats/vendors/nousresearch), [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-9353 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-9353 being exploited in the wild.

**How severe is CVE-2026-9353?** High severity, with a CVSS score of 7.3, published 24 May 2026.

**Which products and versions are affected?** NousResearch Hermes Agent < 0.15.0; hermes-agent (PyPI) ECOSYSTEM:introduced=0,fixed=0.15.0.

**Is there a fix for CVE-2026-9353?** Yes. hermes-agent (PyPI): upgrade to 0.15.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-9353 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-9353?** Check whether you run NousResearch Hermes Agent or hermes-agent (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- hermes-agent (PyPI): upgrade to 0.15.0 or later

  ```sh
  pip install "hermes-agent>=0.15.0"
  ```


## Technical details

A prompt injection vulnerability exists in the Skills Guard Multi-Word Prompt Handler within `agent/skills_guard.py`. The root cause is the use of rigid regular expressions for the `THREAT_PATTERNS` argument, specifically for patterns like 'system prompt override'. Because these patterns do not account for flexible whitespace or intervening words, an attacker can bypass the filter by injecting extraneous words (e.g., 'system prompt temporary override'). This bypass allows the installation of malicious skills that can override system prompts and alter agent behavior. The issue is addressed in version 0.15.0 by implementing more flexible regex matching.

## Affected products

- NousResearch hermes-agent < 0.15.0

## Identifiers

- CVE-2026-9353
- GHSA-238w-f66p-w349
- PYSEC-2026-2509

## Timeline

- 2026-04-24: disclosed: Public disclosure via GitHub Gist and PoC release
- 2026-05-24: advisory: NVD publication date
- 2026-05-26: advisory: GitHub Advisory published
- 2026-06-30: patched: GitHub Advisory updated with patch information

## References

- [https://gist.github.com/YLChen-007/82a3539d6358842e69dfaef0a9fcf14a](https://gist.github.com/YLChen-007/82a3539d6358842e69dfaef0a9fcf14a)
- [https://vuldb.com/submit/812216](https://vuldb.com/submit/812216)
- [https://vuldb.com/vuln/365316](https://vuldb.com/vuln/365316)
- [https://vuldb.com/vuln/365316/cti](https://vuldb.com/vuln/365316/cti)
- [https://github.com/NousResearch/hermes-agent/pull/26852](https://github.com/NousResearch/hermes-agent/pull/26852)

## Related threats

- [NousResearch hermes-agent resource exhaustion in resourceBufferFromUrl](https://junglewise.ai/threats/cve-2026-85107-nousresearch-hermes-agent-resource-exhaustion-in)
- [NousResearch hermes-agent server-side request forgery in Link Title Fetch](https://junglewise.ai/threats/cve-2026-85106-nousresearch-hermes-agent-server-side-request-forgery-in-link)
- [NousResearch hermes-agent authorization bypass in Session Management](https://junglewise.ai/threats/cve-2026-85105-nousresearch-hermes-agent-authorization-bypass-in-session)
- [NousResearch hermes-agent denial of service in MCP Tool](https://junglewise.ai/threats/cve-2026-84289-nousresearch-hermes-agent-denial-of-service-in-mcp-tool)
- [NousResearch hermes-agent denial of service in ACP Prompt Workflow](https://junglewise.ai/threats/cve-2026-84288-nousresearch-hermes-agent-denial-of-service-in-acp-prompt)