ClawHub
Back to skill

Security audit

Bananapro Image Gen

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward image-generation helper, but users should only use it with an API endpoint they trust because prompts, optional images, and API keys are sent to that service.

Before installing or using this skill, decide whether you trust the configured API provider. Prefer the official Gemini endpoint unless you knowingly choose a proxy, avoid confidential prompts or private images, and rotate API keys if they may have been sent to an unintended endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tainted flow: 'url' from os.environ.get (line 56, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Content
# 发送请求
    try:
        response = requests.post(
            url,
            headers={"Content-Type": "application/json"},
            json=payload,
Confidence
95% confidence
Finding
response = requests.post( url, headers={"Content-Type": "application/json"}, json=payload, timeout=120 )

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README tells users to set an API key and use a hosted image-generation service, but it does not clearly disclose that prompts and possibly input images will be transmitted to an external provider. This can lead users to unknowingly send sensitive text or images off-platform, creating privacy, confidentiality, and compliance risks.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill recommends a third-party proxy API as the default path and instructs users to place API keys into environment variables without clearly warning that the proxy operator may observe prompts, metadata, and billing credentials. This creates credential exposure and privacy risk, especially because users may assume the proxy is equivalent to the official provider and the documentation frames it as recommended due to cost and connectivity benefits.

Missing User Warnings

Medium
Confidence
81% confidence
Finding
When --input-image is provided, the file is base64-encoded and sent to the remote image-generation API without any explicit warning or confirmation that local file contents are leaving the host. This can cause unintended disclosure of sensitive images or embedded metadata, especially in an agent setting where users may assume files are processed locally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.