openclaw-marshal Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

openclaw-marshal is an AI agent skill, created by atlaspa and published at openclaw/skills. ClawSecure audited openclaw-marshal across 4 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 12 findings concentrate in Code Injection, Command Injection and Unauthorized Tool Use, including Pattern detected: eval( and Pattern detected: exec(. 10 were rated high or critical severity.

Is openclaw-marshal safe?

ClawSecure audited openclaw-marshal and assigned a security score of 0/100 (High Risk), identifying 12 findings across Code Injection and Command Injection. Review the findings below before installing.

What did ClawSecure find in openclaw-marshal?

ClawSecure identified 12 findings in openclaw-marshal, concentrated in Code Injection, Command Injection and Unauthorized Tool Use. 10 were rated high or critical severity. The most severe include Pattern detected: eval( and Pattern detected: exec(.

How was openclaw-marshal audited?

ClawSecure ran openclaw-marshal through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 4 files from openclaw/skills.

What does a score of 0 mean?

ClawSecure assigned openclaw-marshal a security score of 0/100, placing it in the High Risk range. This is driven by 12 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-marshal

ClawSecure detected 12 security findings in openclaw-marshal, spanning Code Injection, Command Injection, Unauthorized Tool Use and Policy Violation.

critical · Pattern detected: eval(. Command Injection finding detected in scripts/marshal.py:62.
critical · Pattern detected: exec(. Command Injection finding detected in scripts/marshal.py:63.
critical · Pattern detected: compile(. Command Injection finding detected in scripts/marshal.py:68.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in SKILL.md:82.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in scripts/marshal.py:95.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in scripts/marshal.py:95.
high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in README.md.
high · Potentially dangerous code pattern detected: wget.*\|.*sh. Code Injection finding detected in README.md.
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.
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-marshal

Eliminate dynamic code execution

openclaw-marshal 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.

Harden command execution

openclaw-marshal constructs or runs system commands. Validate that commands are built only from trusted inputs, never pass user-controlled strings directly to a shell, and restrict execution to an allow-list of expected commands.

Resolve policy violations

openclaw-marshal 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

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

Related AI Agent Security Audits

byterover-cliScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100

Scanned on February 7, 2026. openclaw-marshal 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