claw-permission-firewall Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

claw-permission-firewall is an AI agent skill, created by bharathjanumpally and published at openclaw/skills. ClawSecure audited claw-permission-firewall across 19 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 75/100 (Medium Risk). The 4 findings concentrate in Permissions Manifest, Malicious Code and Code Injection, including Attempts to access sensitive file: .ssh/ and Potentially dangerous code pattern detected: curl.*\|.*sh. 2 were rated high or critical severity.

Is claw-permission-firewall safe?

ClawSecure audited claw-permission-firewall and assigned a security score of 75/100 (Medium Risk), identifying 4 findings across Permissions Manifest and Malicious Code. Review the findings below before installing.

What did ClawSecure find in claw-permission-firewall?

ClawSecure identified 4 findings in claw-permission-firewall, concentrated in Permissions Manifest, Malicious Code and Code Injection. 2 were rated high or critical severity. The most severe include Attempts to access sensitive file: .ssh/ and Potentially dangerous code pattern detected: curl.*\|.*sh.

How was claw-permission-firewall audited?

ClawSecure ran claw-permission-firewall through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 19 files from openclaw/skills.

What does a score of 75 mean?

ClawSecure assigned claw-permission-firewall a security score of 75/100, placing it in the Medium Risk range. This reflects 4 findings led by Permissions Manifest that warrant review before production 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 claw-permission-firewall

ClawSecure detected 4 security findings in claw-permission-firewall, spanning Permissions Manifest, Malicious Code, Code Injection and Supply Chain.

high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in file-deny-sensitive.json.
high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in SKILL.md.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
moderate · Vulnerability in js-yaml@4.1.0: js-yaml has prototype pollution in.... Supply Chain finding detected in package.json.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for claw-permission-firewall

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.

Audit external network connections

claw-permission-firewall 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

claw-permission-firewall 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.

Update and pin dependencies

claw-permission-firewall 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.

Related Security Research

How to Secure an MCP Server: The 2026 Guide→What Is MCP Security? Model Context Protocol Explained→ClawHavoc Explained: The Malware Family Targeting AI Agents→

Related AI Agent Security Audits

hermes-agentScore 85/100 Agent-ReachScore 85/100 agent-creditScore 75/100 Agent-ReachScore 75/100 agent-skillsScore 85/100

Scanned on February 7, 2026. claw-permission-firewall 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