Wan 2.6 & 2.5 — AI Video & Image Generation by Alibaba

• Outcome: Review
• Latest audit: May 29, 2026 at 9:25 PM UTC
• Version:
  1.0.2

Overview

This is mostly a normal paid AI media-generation skill, but it needs review because one script can use an under-disclosed Google AI Studio path and the activation/API-key scope is broad.

Review before installing. Use it only if you are comfortable with paid Atlas Cloud calls and with the image script's optional Google AI Studio behavior. Avoid setting GEMINI_API_KEY for this skill unless you intend Google to be used, and verify provider choice before sending private prompts, images, audio, or videos.

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: 84% confidence
• Finding: The trigger description is extremely broad and can cause the skill to activate for many generic requests about images, videos, marketing assets, or visual content. Over-triggering is dangerous here because activation leads to external transmission of prompts and media to a third-party API and may incur charges on an unscoped account key.

VirusTotal

66/66 vendors flagged this skill as clean.