Skills
skills/inference-sh-skills/skills/ai-marketing-videos/Gen Agent Trust Hub

ai-marketing-videos

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool via Bash to execute AI models for video and audio synthesis. This usage is explicitly restricted and defined in the allowed-tools configuration.
  • [EXTERNAL_DOWNLOADS]: Provides links to installation instructions and other skills hosted on the vendor's GitHub repository (inference-sh/skills) and official domains (inference.sh). These are recognized as legitimate vendor resources.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it interpolates user-provided text into shell commands and JSON payloads. However, the risk is minimal as the input is primarily used for creative content generation within a controlled CLI environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:28 AM
Security Audit — agent-trust-hub — ai-marketing-videos