← Back to Scanner

project-code-builder Security Audit Report

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

project-code-builder is an AI agent skill, created by Chen Leiyang and published at openclaw/skills. ClawSecure audited project-code-builder across 14 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 35/100 (High Risk). The 6 findings concentrate in Supply Chain and Permissions Manifest, including Vulnerability in simple-git@3.0.0: Remote code execution in simple-git and Vulnerability in simple-git@3.0.0: Command injection in simple-git. 5 were rated high or critical severity.

Is project-code-builder safe?

ClawSecure audited project-code-builder and assigned a security score of 35/100 (High Risk), identifying 6 findings across Supply Chain and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in project-code-builder?

ClawSecure identified 6 findings in project-code-builder, concentrated in Supply Chain and Permissions Manifest. 5 were rated high or critical severity. The most severe include Vulnerability in simple-git@3.0.0: Remote code execution in simple-git and Vulnerability in simple-git@3.0.0: Command injection in simple-git.

How was project-code-builder audited?

ClawSecure ran project-code-builder through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 14 files from openclaw/skills.

What does a score of 35 mean?

ClawSecure assigned project-code-builder a security score of 35/100, placing it in the High Risk range. This is driven by 6 findings led by Supply Chain 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 project-code-builder

ClawSecure detected 6 security findings in project-code-builder, spanning Supply Chain and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for project-code-builder

Update and pin dependencies
project-code-builder depends on packages with supply-chain risk. Pin every dependency to an exact version, update packages with known CVEs to patched releases, and re-audit after each change. ClawSecure checks every dependency against known CVE databases.
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

AI Agent Supply Chain Attacks: How Dependencies Become WeaponsBeyond Static Scans: Why ClawSecure Verifies Agentic Intent

Related AI Agent Security Audits

openclaw-dashboard-repoScore 25/100openclaw-dashboard-repoScore 25/100openclaw-dashboard-repoScore 25/100@martian-engineering/lossless-clawScore 25/100self-improvementScore 25/100

Scanned on February 7, 2026. project-code-builder 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