Visual Gen Ai Language

• Outcome: Pass
• Latest audit: May 28, 2026, 6:48 AM
• Version:
  1.2.1

Overview

This is a markdown-only helper for producing structured image-generation JSON, with no hidden execution, persistence, or local data access found.

This appears safe to install as a prompt-formatting skill. Use normal caution if you pair it with an API execution skill: prompts, images, and generated descriptions sent to Bria or another provider may leave your local environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill advertises very broad triggers such as requests for structured prompts, controllable generation, deterministic image descriptions, or Bria/FIBO structured_prompt format without strong boundaries. Over-broad activation can cause the skill to engage in contexts where it is not intended, increasing prompt-routing mistakes and the chance that unrelated user content is transformed into structured output or sent onward to a paired execution skill.

VirusTotal

66/66 vendors flagged this skill as clean.