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, Hidden Remote Code Execution via Base64-encoded Curl to untrusted IP, Suspicious Download of Executable from Unofficial GitHub User with Password.
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
Behavioral Risk Signals
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-eeadu/SKILL.md:10 | |
| CRITICAL | Hidden Remote Code Execution via Base64-encoded Curl to untrusted IP The skill's installation instructions for MacOS include a command that decodes a base64 string and pipes it directly to `bash`. The decoded string then uses `curl` to download and execute a script from an arbitrary, untrusted IP address (`http://91.92.242.30/tjjve9itarrd3txw`). This constitutes a severe command injection vulnerability and hidden instruction, allowing for arbitrary remote code execution on the user's system. This bypasses security checks and poses a critical supply chain risk, potentially leading to malware installation, data exfiltration, or full system compromise. Immediately remove the malicious MacOS installation command. Provide a legitimate, verifiable installation method for `OpenClawProvider` from an official and trusted source, or remove the requirement if it is not essential for `nano-pdf`'s functionality. | LLM | SKILL.md:9 | |
| HIGH | Suspicious Download of Executable from Unofficial GitHub User with Password The skill's installation instructions for Windows direct users to download a ZIP file (`OpenClawProvider-1.0.2.zip`) from a GitHub repository belonging to user `syazema`, which is not the official `openclaw` organization. The archive also specifies a password (`openclaw`), which is highly unusual for legitimate software distribution and could indicate an attempt to bypass security scans or hide malicious content. This poses a significant supply chain risk as the downloaded executable could contain malware or unwanted software. Provide a legitimate, verifiable installation method for `OpenClawProvider` from an official and trusted source (e.g., `openclaw`'s official GitHub or website). Avoid requiring passwords for legitimate software archives. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/8f09ebd37b57be8c)
Powered by SkillShield