← Back to Scanner

realbrowser Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower
Source:
SHA-256:

realbrowser is an AI agent skill, created by darkamenosa and published at darkamenosa/realbrowser. ClawSecure audited realbrowser across 15 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 85/100 (Safe). The 2 findings concentrate in Permissions Manifest and Code Injection, including Potentially dangerous code pattern detected: eval\( and Missing config.json - agent may not be properly configured. 1 was rated high or critical severity.

Is realbrowser safe?

ClawSecure audited realbrowser and assigned a security score of 85/100 (Safe), identifying 2 findings across Permissions Manifest and Code Injection. Review the findings below before installing.

What did ClawSecure find in realbrowser?

ClawSecure identified 2 findings in realbrowser, concentrated in Permissions Manifest and Code Injection. 1 was rated high or critical severity. The most severe include Potentially dangerous code pattern detected: eval\( and Missing config.json - agent may not be properly configured.

How was realbrowser audited?

ClawSecure ran realbrowser through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 15 files from darkamenosa/realbrowser.

What does a score of 85 mean?

ClawSecure assigned realbrowser a security score of 85/100, placing it in the Safe range. Scores of 80 or above qualify for ClawSecure Verified status, though 1 finding was rated high or critical and warrants review. 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 realbrowser

ClawSecure detected 2 security findings in realbrowser, spanning Permissions Manifest and Code Injection.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for realbrowser

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.
Eliminate dynamic code execution
realbrowser 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.
Pin dependencies to exact versions
Unpinned dependencies allow supply-chain attacks where a compromised version is pulled in automatically. Use exact version numbers in package.json (for example 1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. 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→Why Generic Scanners Fail at AI Agent Security→

Related AI Agent Security Audits

browserScore 95/100summarizeScore 85/100paperclipScore 80/100ai-daily-briefingScore 85/100rag-knowledge-engineScore 95/100

Scanned on June 29, 2026. realbrowser 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