ClawHub
Back to skill

Security audit

Turn a real photo into a custom anime-style avatar, Moments cover, or Twitter/X header.

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill asks for a mew.design API key and photo to generate anime-style social images, and its behavior matches that stated purpose.

Install only if you are comfortable sending a photo and a mew.design API key to the mew.design image API. Prefer a dedicated or revocable key, avoid using it in shared chats, and rotate it after use if you are concerned about chat history exposure.

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
93% confidence
Finding
The manifest description includes a broad installation phrase ('Help me install this skill...') that can overlap with ordinary user language and may cause unintended skill installation or invocation. Because installation changes agent capabilities, ambiguous trigger wording increases the chance of accidental consent or social-engineering-style activation.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The example install intents are generic ('Install this skill', 'Help me install this ClawHub skill') and are not sufficiently scoped to this specific skill. That makes accidental invocation more likely when a user is discussing installation generally, which is risky because the skill later requests credentials and photo uploads.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs users to paste a live mew.design API key directly into chat without any warning about credential sensitivity, scope, retention, or safer handling. Collecting secrets in chat raises the risk of exposure through logs, transcripts, shared devices, or downstream systems, and the key is then used to access an external service on the user's behalf.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.