skills/styleof/superpowers/seedance/Gen Agent Trust Hub

seedance

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides examples of using the belt CLI tool to interact with the Seedance 2.0 API. These commands are typical for interacting with an AI inference platform and do not perform any hidden or malicious operations.
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and documentation from raw.githubusercontent.com/inference-sh/ and inference.sh. These are well-known resources related to the integration of the AI service and are handled as safe configuration fetches.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided strings and URLs (images/videos) to generate content. While this is an ingestion surface for external data, it is the primary purpose of the skill. The instructions use standard JSON structures for inputs, which helps in maintaining clear boundaries for the AI model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:22 PM