ai-marketing-videos

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements the allowed-tools configuration to limit the agent's environment to only the belt CLI, following the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: Dependencies such as the belt CLI and supporting skills are fetched from the platform's official registries. These are expected resources for the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill uses bash commands to automate workflows through the vendor's CLI. The commands are transparent and focused on API interactions with the inference.sh service.
  • [PROMPT_INJECTION]: The skill utilizes a workflow where content generated by one AI model (e.g., a script) is passed as input to other models for video and voiceover generation. This indirect prompt ingestion is a standard design for automated content creation and is well-contained within the platform's tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:02 AM
Security Audit — agent-trust-hub — ai-marketing-videos