outfit-transition-video

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:27 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed WeryAI video-generation helper with sensitive but documented API-key and optional local-image upload behavior.

Install only if you trust this WeryAI integration and are comfortable configuring WERYAI_API_KEY. Prefer public HTTPS image URLs; do not pass local file paths unless you have reviewed the script and intentionally want that image uploaded to WeryAI. Use a scoped or dedicated API key where possible because generation can consume paid credits.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The skill is presented as a narrowly scoped outfit-transition generator, but the documented behavior includes broader capabilities such as arbitrary task status lookups, model enumeration, generic video generation modes, and possible local file upload to a third party. This mismatch expands the trust boundary beyond what a user may reasonably expect, increasing the risk of unintended data disclosure—especially if local image paths are accepted and uploaded externally.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The implicit trigger uses a broad natural-language prompt describing the skill’s domain rather than requiring a clearer invocation boundary, which can cause the skill to activate on ordinary user requests that merely resemble fashion/video-editing intent. In an agent system, overbroad triggering can route unrelated requests into this skill unexpectedly, increasing the chance of inappropriate tool use, policy bypass through misrouting, or unintended external actions.

VirusTotal

66/66 vendors flagged this skill as clean.