explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides a link to installation instructions for the belt CLI tool, hosted on the inference-sh GitHub repository. This is a neutral reference to documentation necessary for the skill's usage.\n- [COMMAND_EXECUTION]: The skill uses the belt CLI to run various AI models for video, image, and audio generation. These shell commands are the intended method of operation for the skill.\n- [PROMPT_INJECTION]: The skill handles user-provided prompt strings for media generation. This represents an indirect prompt injection surface but is essential for the skill's functionality.\n
  • Ingestion points: Prompts used within belt app run commands for various media models in SKILL.md.\n
  • Boundary markers: Prompt data is contained within JSON structures to differentiate it from command logic.\n
  • Capability inventory: Media generation and sequence assembly via the belt CLI.\n
  • Sanitization: Input is passed directly to the models as described in the workflow templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:09 PM
Security Audit — agent-trust-hub — explainer-video-guide