Security Audit

nano-pdf

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CRITICAL

Scanned 3 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

nano-pdf 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, Obfuscated Remote Script Execution from Suspicious IP (MacOS), Password-Protected Archive for Dependency Installation (Windows).

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 14, 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

1 finding

Filesystem Write

1 finding

Shell Execution

3 findings

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/nano-pdf-n2hcr/SKILL.md:10
CRITICAL	Obfuscated Remote Script Execution from Suspicious IP (MacOS) The MacOS installation instructions for 'OpenClawProvider' contain a base64-encoded command that, when decoded and executed, downloads and runs an arbitrary shell script from an unverified IP address (http://91.92.242.30/tjjve9itarrd3txw). This constitutes a severe supply chain risk, allowing arbitrary code execution on the user's system, which could lead to data exfiltration, credential harvesting, or further system compromise. The use of base64 encoding also indicates a hidden instruction. Immediately remove this malicious installation command. Provide a secure, verifiable, and transparent method for installing 'OpenClawProvider', preferably from a trusted package repository, a signed executable, or a well-known distribution channel. Avoid direct execution of scripts from untrusted sources or obfuscated commands.	LLM	SKILL.md:11
HIGH	Password-Protected Archive for Dependency Installation (Windows) The Windows installation instructions for 'OpenClawProvider' require downloading a password-protected ZIP file ('OpenClawProvider-1.0.2.zip') from GitHub releases. Requiring a password ('openclaw') for extraction is an unusual practice that can hinder security analysis and hide malicious content, significantly increasing supply chain risk by making it difficult for users or automated tools to inspect the contents before execution. Provide a transparent and easily verifiable installation method for 'OpenClawProvider' on Windows, such as an unsigned executable or a standard package manager, without requiring password-protected archives. If a password is truly necessary for some legitimate reason, explain the security rationale and provide a mechanism for verifying the archive's integrity (e.g., checksums).	LLM	SKILL.md:7

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/fe80815ecf640a23.svg)](https://skillshield.io/report/fe80815ecf640a23)