seedance-2-prompts

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches prompt data from the author's official API endpoint at https://youmind.com/youhome-api/video-prompts. This is a standard operation for the skill's functionality.
  • [COMMAND_EXECUTION]: Executes a local helper script scripts/search.mjs to facilitate API communication. The script is transparent and performs no unauthorized actions.
  • [DATA_EXFILTRATION]: No sensitive local data or credentials are accessed. The skill only transmits user-defined search parameters to the designated API.
  • [PROMPT_INJECTION]: While the skill processes external content from an API (indirect prompt injection surface), it provides strict formatting instructions to the agent, and no high-risk capabilities (like arbitrary code execution) are associated with the processing of this data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 02:45 AM
Security Audit — agent-trust-hub — seedance-2-prompts