agent-builder Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

agent-builder is an AI agent skill, created by plgonzalezrx8 and published at openclaw/skills. ClawSecure audited agent-builder across 5 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 8 findings concentrate in Malicious Code, Permissions Manifest and Policy Violation, including Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: MEMORY.md. 6 were rated high or critical severity.

Is agent-builder safe?

ClawSecure audited agent-builder and assigned a security score of 35/100 (High Risk), identifying 8 findings across Malicious Code and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in agent-builder?

ClawSecure identified 8 findings in agent-builder, concentrated in Malicious Code, Permissions Manifest and Policy Violation. 6 were rated high or critical severity. The most severe include Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: MEMORY.md.

How was agent-builder audited?

ClawSecure ran agent-builder through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 5 files from openclaw/skills.

What does a score of 35 mean?

ClawSecure assigned agent-builder a security score of 35/100, placing it in the High Risk range. This is driven by 8 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 agent-builder

ClawSecure detected 8 security findings in agent-builder, spanning Malicious Code, Permissions Manifest and Policy Violation.

high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in openclaw-workspace.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in openclaw-workspace.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in templates.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in templates.md.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
info · Missing License Declaration. Policy Violation finding detected in SKILL.md.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for agent-builder

Audit external network connections

agent-builder 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.

Resolve policy violations

agent-builder trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.

Related Security Research

ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

agent-builderScore 35/100 agent-builderScore 35/100 agent-builderScore 35/100 agent-builderScore 35/100 agent-builderScore 35/100

Scanned on March 9, 2026. agent-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