storyboard-creation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves installation and setup documentation from the inference-sh organization's repository on GitHub.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to perform image generation and image processing, which is the primary intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses user-supplied descriptions to build prompts for image generation, creating a surface for potential indirect prompt injection.
  • Ingestion points: User-provided scene details and shot descriptions are interpolated into command strings.
  • Boundary markers: The templates do not utilize specific delimiters to isolate user-provided content.
  • Capability inventory: The skill executes shell commands via the belt tool for remote image generation.
  • Sanitization: There is no evidence of input validation or sanitization before user data is included in prompt templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:21 PM
Security Audit — agent-trust-hub — storyboard-creation