Skills
Navigate
skills/whytryharder/superpowers/book-cover-design/Gen Agent Trust Hub

book-cover-design

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing external CLI tools and related skills from the belt-sh and inference-sh GitHub organizations.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI via the Bash tool to interact with remote AI models for image generation, upscaling, and editing. The frontmatter uses the allowed-tools field to limit Bash execution strictly to the belt utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses shell command templates where user-supplied descriptions are passed as arguments to the belt command, creating an attack surface for indirect prompt injection.
  • Ingestion points: User-provided book cover prompts and image file paths.
  • Boundary markers: The skill does not define specific delimiters or instructions to isolate user input from the command context.
  • Capability inventory: The skill is permitted to run belt CLI commands through Bash for remote model inference.
  • Sanitization: There is no evidence of input validation or sanitization within the skill instructions before interpolation into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 05:50 AM