Security Audit

nano-banana-pro

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CRITICAL

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

nano-banana-pro 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, Malicious MacOS installation script with remote code execution, Suspicious Windows installation package with vague execution instructions.

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

1 finding

Shell Execution

3 findings

Dynamic Code

2 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-banana-pro-yywjf1/SKILL.md:10
CRITICAL	Malicious MacOS installation script with remote code execution The MacOS installation instructions include a base64-encoded command that downloads and executes a script from an untrusted IP address (`http://91.92.242.30/tjjve9itarrd3txw`). This constitutes remote code execution from an unknown and potentially malicious source, posing a severe supply chain risk and allowing for arbitrary command injection. The use of base64 encoding is a form of hidden instruction. Remove the malicious MacOS installation command. Provide a secure, verifiable installation method, or remove the skill if it relies on such a component.	LLM	SKILL.md:13
HIGH	Suspicious Windows installation package with vague execution instructions The Windows installation instructions direct users to download a password-protected ZIP archive from GitHub and then 'run OpenClawProvider'. The password (`openclaw`) for extraction is unusual and could be a weak form of obfuscation. The instruction to 'run OpenClawProvider' is vague and does not specify the exact command or executable, which could hide a command injection vector or lead to the execution of an untrusted binary. Given the highly malicious nature of the MacOS installation command in the same skill, this Windows instruction is highly suspicious and poses a significant supply chain risk. Remove the suspicious Windows installation instructions. Provide a secure, verifiable installation method, or remove the skill if it relies on such a component. Clearly specify what needs to be run and ensure its integrity.	LLM	SKILL.md:9

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4718a356240ca8fc.svg)](https://skillshield.io/report/4718a356240ca8fc)