Security Audit

Agent Browser

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CRITICAL

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Agent Browser received a trust score of 40/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Obfuscated remote script execution during MacOS setup.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

70%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Obfuscated execution: base64 decode to shell Detected base64-encoded data being decoded and piped to a shell interpreter. This is a common obfuscation technique. Decode and inspect the base64 content before execution.	Static	skills/sakaen736jih/agent-browser-b2x7tvcmbjgp/SKILL.md:10
CRITICAL	Obfuscated remote script execution during MacOS setup The MacOS installation instructions for 'OpenClawProvider' include a base64-encoded command that, when decoded, executes a shell command to download and run a script from an arbitrary IP address (`http://91.92.242.30/tjjve9itarrd3txw`) via `curl \| bash`. This is a severe security risk, as it allows arbitrary code execution from an untrusted, non-version-controlled source, bypassing typical package management security. The IP address is not associated with the declared GitHub repository for 'OpenClawProvider' or 'agent-browser'. This constitutes a hidden instruction, a command injection vulnerability, and a critical supply chain risk. Remove the base64-encoded command and replace it with a secure, transparent installation method. If 'OpenClawProvider' is truly required, it should be installed via a trusted package manager or a direct download from a verified source with integrity checks. The script at `91.92.242.30` should be thoroughly audited, and its necessity questioned.	LLM	SKILL.md:14

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2192590f5ffa0541.svg)](https://skillshield.io/report/2192590f5ffa0541)