← Back to Scanner

bb-browser Security Audit Report

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

bb-browser is an AI agent skill, created by epiral and published at epiral/bb-browser. ClawSecure audited bb-browser across 56 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 63/100 (Medium Risk). The 6 findings concentrate in Supply Chain and Permissions Manifest, including Vulnerability in @modelcontextprotocol/sdk@1.12.1:... and Vulnerability in @modelcontextprotocol/sdk@1.12.1: Anthropic's MCP.... 3 were rated high or critical severity.

Is bb-browser safe?

ClawSecure audited bb-browser and assigned a security score of 63/100 (Medium Risk), identifying 6 findings across Supply Chain and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in bb-browser?

ClawSecure identified 6 findings in bb-browser, concentrated in Supply Chain and Permissions Manifest. 3 were rated high or critical severity. The most severe include Vulnerability in @modelcontextprotocol/sdk@1.12.1:... and Vulnerability in @modelcontextprotocol/sdk@1.12.1: Anthropic's MCP....

How was bb-browser audited?

ClawSecure ran bb-browser through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 56 files from epiral/bb-browser.

What does a score of 63 mean?

ClawSecure assigned bb-browser a security score of 63/100, placing it in the Medium Risk range. This reflects 6 findings led by Supply Chain 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 bb-browser

ClawSecure detected 6 security findings in bb-browser, spanning Supply Chain and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for bb-browser

Update and pin dependencies
bb-browser 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.
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.
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

AI Agent Supply Chain Attacks: How Dependencies Become WeaponsBeyond Static Scans: Why ClawSecure Verifies Agentic Intent

Related AI Agent Security Audits

c81972687d0e5a06Score 75/1007caf5d769dee89c3Score 55/10049d9c51b3ba29229Score 75/10019af8eafb16b72f6Score 75/1003f5bb9462d7cb920Score 75/100

Scanned on April 19, 2026. bb-browser 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