ClawHub

Spark Image

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed paid image-generation integration, with the main cautions being API key handling and avoiding sensitive prompts.

Install only if you are comfortable sending image prompts to image.open-idea.net and paying for generated images. Keep IMAGE_GATEWAY_API_KEY out of chat logs, screenshots, shell history, and version control, and confirm the estimated cost before generation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list contains broad, everyday phrases like “画图”, “制作图片”, and style keywords such as “油画风格” that can match ordinary user requests too loosely and cause unintended invocation. In this skill, unintended activation is more concerning because invocation can transmit user prompts to a third-party image service and may incur billing, creating both privacy and cost exposure.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The document instructs users to place a live API key in an environment variable and to test it with a command containing a Bearer token, but it provides no guidance on secure storage, shell history exposure, least-privilege handling, or key rotation. In a skill that depends on bearer-token authentication for billable image generation, this omission increases the chance of credential leakage and unauthorized usage.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal