Seedance 2.0 Video

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:17 PM UTC
• Version:
  1.0.0

Overview

This skill is a straightforward PoYo video-generation integration, with normal external API and API-key use for that purpose.

Install only if you are comfortable sending generation prompts, image URLs, job settings, task IDs, and optional webhook notifications to PoYo. Prefer setting POYO_API_KEY as an environment variable instead of passing it on the command line, and avoid using sensitive prompts or private image URLs unless PoYo's privacy and retention terms fit your needs.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The workflow instructs the agent to send Bearer-authenticated JSON to an external API but does not warn users that prompts, images, and possibly callback metadata will be transmitted to a third party. In an agent setting, this omission can cause unintentional disclosure of sensitive user content to an external service.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The skill requires `POYO_API_KEY` but provides no handling guidance or warning about credential sensitivity. Without explicit safeguards, users or downstream tooling may expose the key in logs, prompts, shell history, or shared payload examples.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation encourages use of a `callback_url` webhook but does not warn that prompts, task identifiers, status, and potentially other job metadata will be sent to the specified third-party endpoint. In a skill context, users may supply callback destinations they do not control or may not realize that sensitive creative inputs and metadata are being forwarded off-platform.

VirusTotal

64/64 vendors flagged this skill as clean.