openclaw-skills-security Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

openclaw-skills-security is an AI agent skill, created by useai-pro and published at useai-pro/openclaw-skills-security. ClawSecure audited openclaw-skills-security across 32 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 15/100 (High Risk). The 9 findings concentrate in Malicious Code, Code Injection and Permissions Manifest, including Attempts to access sensitive file: .ssh/ and Attempts to access sensitive file: .ssh/. 8 were rated high or critical severity.

Is openclaw-skills-security safe?

ClawSecure audited openclaw-skills-security and assigned a security score of 15/100 (High Risk), identifying 9 findings across Malicious Code and Code Injection. Review the findings below before installing.

What did ClawSecure find in openclaw-skills-security?

ClawSecure identified 9 findings in openclaw-skills-security, concentrated in Malicious Code, Code Injection and Permissions Manifest. 8 were rated high or critical severity. The most severe include Attempts to access sensitive file: .ssh/ and Attempts to access sensitive file: .ssh/.

How was openclaw-skills-security audited?

ClawSecure ran openclaw-skills-security through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 32 files from useai-pro/openclaw-skills-security.

What does a score of 15 mean?

ClawSecure assigned openclaw-skills-security a security score of 15/100, placing it in the High Risk range. This is driven by 9 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 openclaw-skills-security

ClawSecure detected 9 security findings in openclaw-skills-security, spanning Malicious Code, Code Injection and Permissions Manifest.

high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in config-hardening-checklist.md.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in incident-response-playbook.md.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in SKILL.md.
high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in AUDIT.md.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for openclaw-skills-security

Audit external network connections

openclaw-skills-security 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

openclaw-skills-security 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 Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

clawdtmScore 0/100 awesome-openclaw-skillsScore 0/100 fzfScore 25/100 gnoScore 5/100 understand-anythingScore 0/100

Scanned on March 19, 2026. openclaw-skills-security 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