ClawHub
Back to skill

Security audit

Vgl

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only image prompt formatting skill with no hidden code or system access, though its trigger wording is somewhat broad.

Install this if you want structured JSON prompts for Bria-style image generation. Review generated prompts before sending them to an image model, especially prompts that describe people, and keep API keys under your own control.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description uses very broad trigger language such as requests for structured prompts, controllable generation, deterministic image descriptions, and Bria/FIBO structured_prompt format. Overly broad activation criteria can cause the skill to engage in contexts where it was not intended, increasing the chance of prompt collisions, incorrect routing, or accidental handling of unrelated user requests.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.