← Back to Scanner

hermes-agent Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower
Source:
SHA-256:

hermes-agent is an AI agent skill, created by nousresearch and published at nousresearch/hermes-agent. ClawSecure audited hermes-agent across 50 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 13 findings concentrate in Malicious Code, Code Injection and Permissions Manifest, including Attempts to access sensitive file: .ssh/ and Attempts to access sensitive file: MEMORY.md. 12 were rated high or critical severity.

Is hermes-agent safe?

ClawSecure audited hermes-agent and assigned a security score of 0/100 (High Risk), identifying 13 findings across Malicious Code and Code Injection. Review the findings below before installing.

What did ClawSecure find in hermes-agent?

ClawSecure identified 13 findings in hermes-agent, concentrated in Malicious Code, Code Injection and Permissions Manifest. 12 were rated high or critical severity. The most severe include Attempts to access sensitive file: .ssh/ and Attempts to access sensitive file: MEMORY.md.

How was hermes-agent audited?

ClawSecure ran hermes-agent through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 50 files from nousresearch/hermes-agent.

What does a score of 0 mean?

ClawSecure assigned hermes-agent a security score of 0/100, placing it in the High Risk range. This is driven by 13 findings led by Malicious Code that should be addressed before use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).

Audit Findings for hermes-agent

ClawSecure detected 13 security findings in hermes-agent, spanning Malicious Code, Code Injection and Permissions Manifest.

Showing the 12 highest-severity of 13 findings. The full interactive list appears below.

3-Layer Audit Protocol

Security Recommendations for hermes-agent

Audit external network connections
hermes-agent connects to external endpoints. Verify every outbound connection goes to a trusted destination. Unauthorized callbacks are a primary indicator of ClawHavoc malware and data exfiltration. ClawSecure's proprietary engine monitors for known malicious endpoints including C2 infrastructure.
Eliminate dynamic code execution
hermes-agent evaluates code at runtime (for example eval or dynamic exec). Remove dynamic evaluation of untrusted input, and where code generation is unavoidable, sandbox it and validate every input.
Add a config.json permissions manifest
A config.json file declares what an agent component can access: file system, network, shell execution and more. Without it, users have no visibility into what the component can do before installing. This is the single most impactful security improvement for any AI agent skill.

Related Security Research

ClawHavoc Explained: The Malware Family Targeting AI AgentsBeyond Static Scans: Why ClawSecure Verifies Agentic Intent

Related AI Agent Security Audits

AI-Agent-Risk-EvaluationScore 0/100GUI Agent HarnessScore 0/100braindbScore 0/100System Health Monitor ProScore 0/100clawhubScore 0/100

Scanned on July 22, 2026. hermes-agent is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.

Start Your Free Scan