← Back to Scanner

homunculus-code Security Audit Report

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

homunculus-code is an AI agent skill, created by Javan <https://github.com/JavanC> and published at JavanC/Homunculus. ClawSecure audited homunculus-code across 71 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 5/100 (High Risk). The 10 findings concentrate in Malicious Code and Permissions Manifest, including Attempts to access sensitive file: MEMORY.md and Attempts to access sensitive file: SOUL.md. 9 were rated high or critical severity.

Is homunculus-code safe?

ClawSecure audited homunculus-code and assigned a security score of 5/100 (High Risk), identifying 10 findings across Malicious Code and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in homunculus-code?

ClawSecure identified 10 findings in homunculus-code, concentrated in Malicious Code and Permissions Manifest. 9 were rated high or critical severity. The most severe include Attempts to access sensitive file: MEMORY.md and Attempts to access sensitive file: SOUL.md.

How was homunculus-code audited?

ClawSecure ran homunculus-code through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 71 files from JavanC/Homunculus.

What does a score of 5 mean?

ClawSecure assigned homunculus-code a security score of 5/100, placing it in the High Risk range. This is driven by 10 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 homunculus-code

ClawSecure detected 10 security findings in homunculus-code, spanning Malicious Code and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for homunculus-code

Audit external network connections
homunculus-code 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.
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.
Pin dependencies to exact versions
Unpinned dependencies allow supply-chain attacks where a compromised version is pulled in automatically. Use exact version numbers in package.json (for example 1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.

Related Security Research

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

Related AI Agent Security Audits

memUScore 0/100awesome-openclaw-skillsScore 0/100understand-anythingScore 0/10062ac696296b54aadScore 0/1006bc837afc1a86e89Score 0/100

Scanned on June 22, 2026. homunculus-code 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