ClawHub
Back to skill

Security audit

Publish Skill

Security checks across malware telemetry and agentic risk

Overview

This is a simple image-generation skill whose main risk is expected use of third-party image APIs with the user's own API keys.

Install only if you are comfortable sending image prompts to the configured provider and using that provider's API quota. Configure only the provider key you intend to use, prefer revocable or limited keys where available, and avoid including secrets or sensitive personal/business data in prompts.

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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to match ordinary image-generation requests, which can cause the agent to invoke this skill in many contexts without clear boundaries. Because the skill routes user prompts to external providers using configured API keys, over-broad invocation increases the chance of unintended third-party data disclosure and unnecessary tool use.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The generic examples like '帮我生成…' and '画一幅…' are common user phrases that overlap with normal conversation, making accidental invocation more likely. In this skill's context, accidental invocation matters because user prompts may be transmitted to third-party image services and consume paid API quota.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill does not disclose that prompts and related content will be sent to third-party providers such as MiniMax, OpenAI, or Stability. This creates a real privacy and compliance risk because users may include sensitive personal, business, or regulated data in prompts without understanding that it leaves the local agent environment.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.