video-prompting-guide

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains educational content and prompt templates designed to improve AI video generation quality. No malicious patterns, obfuscation, or data exfiltration attempts were found.
  • [COMMAND_EXECUTION]: The skill demonstrates the use of the 'infsh' CLI tool, which is the official tool for the 'inference-shell' vendor. The examples provided are standard commands for running video generation apps (e.g., google/veo-3-1-fast) using valid JSON inputs.
  • [EXTERNAL_DOWNLOADS]: The documentation suggests installing related skills using 'npx skills add'. All referenced packages (e.g., inference-sh/skills@agent-tools) belong to the same trusted vendor ecosystem as the skill author.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:31 PM