openclaw-arbiter Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

openclaw-arbiter is an AI agent skill, created by atlaspa and published at atlaspa/openclaw-arbiter. ClawSecure audited openclaw-arbiter across 3 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 Code Injection, Policy Violation and Permissions Manifest, including Potentially dangerous code pattern detected: eval\( and Potentially dangerous code pattern detected: exec\(. 6 were rated high or critical severity.

Is openclaw-arbiter safe?

ClawSecure audited openclaw-arbiter and assigned a security score of 35/100 (High Risk), identifying 8 findings across Code Injection and Policy Violation. Review the findings below before installing.

What did ClawSecure find in openclaw-arbiter?

ClawSecure identified 8 findings in openclaw-arbiter, concentrated in Code Injection, Policy Violation and Permissions Manifest. 6 were rated high or critical severity. The most severe include Potentially dangerous code pattern detected: eval\( and Potentially dangerous code pattern detected: exec\(.

How was openclaw-arbiter audited?

ClawSecure ran openclaw-arbiter through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 3 files from atlaspa/openclaw-arbiter.

What does a score of 35 mean?

ClawSecure assigned openclaw-arbiter a security score of 35/100, placing it in the High Risk range. This is driven by 8 findings led by Code Injection 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-arbiter

ClawSecure detected 8 security findings in openclaw-arbiter, spanning Code Injection, Policy Violation and Permissions Manifest.

high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in README.md.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in README.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in SKILL.md.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in SKILL.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in arbiter.py.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in arbiter.py.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
info · Skill manifest does not include a 'license' field. Specifying a license.... Policy Violation finding detected in SKILL.md.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for openclaw-arbiter

Eliminate dynamic code execution

openclaw-arbiter 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.

Resolve policy violations

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

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

Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

ClawSecScore 45/100 claude-memScore 35/100 fzfScore 25/100 open-webuiScore 35/100 gnoScore 45/100

Scanned on May 4, 2026. openclaw-arbiter 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