Skills
Navigate
skills/inference-sh/skills/book-cover-design/Gen Agent Trust Hub

book-cover-design

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to construct and execute shell commands by interpolating user-provided text into JSON payloads for image generation.
  • Ingestion points: User descriptions for book cover concepts are processed into prompts for the belt CLI tool.
  • Boundary markers: Commands use JSON structure within shell arguments to delimit data.
  • Capability inventory: The skill utilizes the Bash tool to execute belt app run commands.
  • Sanitization: No explicit sanitization or escaping of the user-provided prompt string is shown before interpolation into the JSON object.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the belt CLI and fetch configuration from the vendor's official GitHub repository.
  • [COMMAND_EXECUTION]: The skill leverages the belt command-line interface to interact with remote AI models for image generation and refinement.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:33 AM